Skip to content

speech_to_text

mindnlp.transformers.models.speech_to_text.configuration_speech_to_text

Speech2Text model configuration

mindnlp.transformers.models.speech_to_text.configuration_speech_to_text.Speech2TextConfig

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [Speech2TextModel]. It is used to instantiate a Speech2Text model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Speech2Text facebook/s2t-small-librispeech-asr architecture.

Configuration objects inherit from [PretrainedConfig] and can be used to control the model outputs. Read the documentation from [PretrainedConfig] for more information.

PARAMETER DESCRIPTION
vocab_size

Vocabulary size of the Speech2Text model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [Speech2TextModel]

TYPE: `int`, *optional*, defaults to 10000 DEFAULT: 10000

encoder_layers

Number of encoder layers.

TYPE: `int`, *optional*, defaults to 12 DEFAULT: 12

encoder_ffn_dim

Dimensionality of the "intermediate" (often named feed-forward) layer in encoder.

TYPE: `int`, *optional*, defaults to 2048 DEFAULT: 2048

encoder_attention_heads

Number of attention heads for each attention layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 4 DEFAULT: 4

decoder_layers

Number of decoder layers.

TYPE: `int`, *optional*, defaults to 6 DEFAULT: 6

decoder_ffn_dim

Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.

TYPE: `int`, *optional*, defaults to 2048 DEFAULT: 2048

decoder_attention_heads

Number of attention heads for each attention layer in the Transformer decoder.

TYPE: `int`, *optional*, defaults to 4 DEFAULT: 4

encoder_layerdrop

The LayerDrop probability for the encoder. See the LayerDrop paper for more details.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

decoder_layerdrop

The LayerDrop probability for the decoder. See the LayerDrop paper for more details.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

use_cache

Whether the model should return the last key/values attentions (not used by all models).

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

is_encoder_decoder

Whether the model is set up as an encoder-decoder architecture for sequence-to-sequence tasks.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

activation_function

The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.

TYPE: `str` or `function`, *optional*, defaults to `"relu"` DEFAULT: 'relu'

d_model

Dimensionality of the layers and the pooler layer.

TYPE: `int`, *optional*, defaults to 256 DEFAULT: 256

dropout

The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

attention_dropout

The dropout ratio for the attention probabilities.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

activation_dropout

The dropout ratio for activations inside the fully connected layer.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

init_std

The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

TYPE: `float`, *optional*, defaults to 0.02 DEFAULT: 0.02

decoder_start_token_id

The initial token ID of the decoder when decoding sequences.

TYPE: `int`, *optional*, defaults to 2 DEFAULT: 2

scale_embedding

Whether the embeddings are scaled by the square root of d_model.

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

pad_token_id

Padding token id.

TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1

bos_token_id

The id of the beginning-of-sequence token.

TYPE: `int`, *optional*, defaults to 0 DEFAULT: 0

eos_token_id

The id of the end-of-sequence token.

TYPE: `int`, *optional*, defaults to 2 DEFAULT: 2

max_source_positions

The maximum sequence length of log-mel filter-bank features that this model might ever be used with.

TYPE: `int`, *optional*, defaults to 6000 DEFAULT: 6000

max_target_positions

The maximum sequence length that this model might ever be used with. Typically, set this to something large just in case (e.g., 512 or 1024 or 2048).

TYPE: `int`, *optional*, defaults to 1024 DEFAULT: 1024

num_conv_layers

Number of 1D convolutional layers in the conv module.

TYPE: `int`, *optional*, defaults to 2 DEFAULT: 2

conv_kernel_sizes

A tuple of integers defining the kernel size of each 1D convolutional layer in the conv module. The length of conv_kernel_sizes has to match num_conv_layers.

TYPE: `Tuple[int]`, *optional*, defaults to `(5, 5)` DEFAULT: (5, 5)

conv_channels

An integer defining the number of output channels of each convolution layers except the final one in the conv module.

TYPE: `int`, *optional*, defaults to 1024 DEFAULT: 1024

input_feat_per_channel

An integer specifying the size of feature vector. This is also the dimensions of log-mel filter-bank features.

TYPE: `int`, *optional*, defaults to 80 DEFAULT: 80

input_channels

An integer specifying number of input channels of the input feature vector.

TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1

Example 
>>> from transformers import Speech2TextConfig, Speech2TextModel
...
>>> # Initializing a Speech2Text s2t_transformer_s style configuration
>>> configuration = Speech2TextConfig()
...
>>> # Initializing a model (with random weights) from the s2t_transformer_s style configuration
>>> model = Speech2TextModel(configuration)
...
>>> # Accessing the model configuration
>>> configuration = model.config
Source code in mindnlp/transformers/models/speech_to_text/configuration_speech_to_text.py 
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
class Speech2TextConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`Speech2TextModel`]. It is used to instantiate a
    Speech2Text model according to the specified arguments, defining the model architecture. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the Speech2Text
    [facebook/s2t-small-librispeech-asr](https://huggingface.co/facebook/s2t-small-librispeech-asr) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.


    Args:
        vocab_size (`int`, *optional*, defaults to 10000):
            Vocabulary size of the Speech2Text model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling [`Speech2TextModel`]
        encoder_layers (`int`, *optional*, defaults to 12):
            Number of encoder layers.
        encoder_ffn_dim (`int`, *optional*, defaults to 2048):
            Dimensionality of the "intermediate" (often named feed-forward) layer in encoder.
        encoder_attention_heads (`int`, *optional*, defaults to 4):
            Number of attention heads for each attention layer in the Transformer encoder.
        decoder_layers (`int`, *optional*, defaults to 6):
            Number of decoder layers.
        decoder_ffn_dim (`int`, *optional*, defaults to 2048):
            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
        decoder_attention_heads (`int`, *optional*, defaults to 4):
            Number of attention heads for each attention layer in the Transformer decoder.
        encoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the encoder. See the [LayerDrop paper](https://arxiv.org/abs/1909.11556) for
            more details.
        decoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the decoder. See the [LayerDrop paper](https://arxiv.org/abs/1909.11556) for
            more details.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether the model should return the last key/values attentions (not used by all models).
        is_encoder_decoder (`bool`, *optional*, defaults to `True`):
            Whether the model is set up as an encoder-decoder architecture for sequence-to-sequence tasks.
        activation_function (`str` or `function`, *optional*, defaults to `"relu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        d_model (`int`, *optional*, defaults to 256):
            Dimensionality of the layers and the pooler layer.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        activation_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for activations inside the fully connected layer.
        init_std (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        decoder_start_token_id (`int`, *optional*, defaults to 2):
            The initial token ID of the decoder when decoding sequences.
        scale_embedding (`bool`, *optional*, defaults to `True`):
            Whether the embeddings are scaled by the square root of `d_model`.
        pad_token_id (`int`, *optional*, defaults to 1):
            Padding token id.
        bos_token_id (`int`, *optional*, defaults to 0):
            The id of the beginning-of-sequence token.
        eos_token_id (`int`, *optional*, defaults to 2):
            The id of the end-of-sequence token.
        max_source_positions (`int`, *optional*, defaults to 6000):
            The maximum sequence length of log-mel filter-bank features that this model might ever be used with.
        max_target_positions (`int`, *optional*, defaults to 1024):
            The maximum sequence length that this model might ever be used with. Typically, set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        num_conv_layers (`int`, *optional*, defaults to 2):
            Number of 1D convolutional layers in the conv module.
        conv_kernel_sizes (`Tuple[int]`, *optional*, defaults to `(5, 5)`):
            A tuple of integers defining the kernel size of each 1D convolutional layer in the conv module. The length
            of `conv_kernel_sizes` has to match `num_conv_layers`.
        conv_channels (`int`, *optional*, defaults to 1024):
            An integer defining the number of output channels of each convolution layers except the final one in the
            conv module.
        input_feat_per_channel (`int`, *optional*, defaults to 80):
            An integer specifying the size of feature vector. This is also the dimensions of log-mel filter-bank
            features.
        input_channels (`int`, *optional*, defaults to 1):
            An integer specifying number of input channels of the input feature vector.

    Example:
        ```python
        >>> from transformers import Speech2TextConfig, Speech2TextModel
        ...
        >>> # Initializing a Speech2Text s2t_transformer_s style configuration
        >>> configuration = Speech2TextConfig()
        ...
        >>> # Initializing a model (with random weights) from the s2t_transformer_s style configuration
        >>> model = Speech2TextModel(configuration)
        ...
        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "speech_to_text"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

    def __init__(
        self,
        vocab_size=10000,
        encoder_layers=12,
        encoder_ffn_dim=2048,
        encoder_attention_heads=4,
        decoder_layers=6,
        decoder_ffn_dim=2048,
        decoder_attention_heads=4,
        encoder_layerdrop=0.0,
        decoder_layerdrop=0.0,
        use_cache=True,
        is_encoder_decoder=True,
        activation_function="relu",
        d_model=256,
        dropout=0.1,
        attention_dropout=0.0,
        activation_dropout=0.0,
        init_std=0.02,
        decoder_start_token_id=2,
        scale_embedding=True,
        pad_token_id=1,
        bos_token_id=0,
        eos_token_id=2,
        max_source_positions=6000,
        max_target_positions=1024,
        num_conv_layers=2,
        conv_kernel_sizes=(5, 5),
        conv_channels=1024,
        input_feat_per_channel=80,
        input_channels=1,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.d_model = d_model
        self.encoder_ffn_dim = encoder_ffn_dim
        self.encoder_layers = encoder_layers
        self.encoder_attention_heads = encoder_attention_heads
        self.decoder_ffn_dim = decoder_ffn_dim
        self.decoder_layers = decoder_layers
        self.decoder_attention_heads = decoder_attention_heads
        self.dropout = dropout
        self.attention_dropout = attention_dropout
        self.activation_dropout = activation_dropout
        self.activation_function = activation_function
        self.init_std = init_std
        self.encoder_layerdrop = encoder_layerdrop
        self.decoder_layerdrop = decoder_layerdrop
        self.use_cache = use_cache
        self.num_hidden_layers = encoder_layers
        self.scale_embedding = scale_embedding  # scale factor will be sqrt(d_model) if True
        self.max_source_positions = max_source_positions
        self.max_target_positions = max_target_positions
        self.num_conv_layers = num_conv_layers
        self.conv_kernel_sizes = list(conv_kernel_sizes)
        self.conv_channels = conv_channels
        self.input_feat_per_channel = input_feat_per_channel
        self.input_channels = input_channels

        if len(self.conv_kernel_sizes) != self.num_conv_layers:
            raise ValueError(
                "Configuration for convolutional module is incorrect. "
                "It is required that `len(config.conv_kernel_sizes)` == `config.num_conv_layers` "
                f"but is `len(config.conv_kernel_sizes) = {len(self.conv_kernel_sizes)}`, "
                f"`config.num_conv_layers = {self.num_conv_layers}`."
            )

        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            is_encoder_decoder=is_encoder_decoder,
            decoder_start_token_id=decoder_start_token_id,
            **kwargs,
        )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text

PyTorch Speech2Text model.

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Conv1dSubsampler

Bases: Module

Convolutional subsampler: a stack of 1D convolution (along temporal dimension) followed by non-linear activation via gated linear units (https://arxiv.org/abs/1911.08460)

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
class Conv1dSubsampler(nn.Module):
    """
    Convolutional subsampler: a stack of 1D convolution (along temporal dimension) followed by non-linear activation
    via gated linear units (https://arxiv.org/abs/1911.08460)
    """

    def __init__(self, config):
        super(Conv1dSubsampler, self).__init__()
        self.config = config
        self.num_layers = config.num_conv_layers
        self.in_channels = config.input_feat_per_channel * config.input_channels
        self.mid_channels = config.conv_channels
        self.out_channels = config.d_model
        self.kernel_sizes = config.conv_kernel_sizes

        self.conv_layers = nn.ModuleList(
            [nn.Conv1d(
                self.in_channels if i == 0 else self.mid_channels // 2,
                self.mid_channels if i < self.num_layers - 1 else self.out_channels * 2,
                kernel_size=k,
                stride=2,
                padding=k // 2,
                pad_mode="pad"
            )
            for i, k in enumerate(self.kernel_sizes)]
        )

    def forward(self, input_features):
        # hidden_states = input_features.transpose(1, 2) # -> B x (C x D) x T
        hidden_states = input_features.swapaxes(1, 2)
        for conv in self.conv_layers:
            hidden_states = conv(hidden_states)
            hidden_states = mindspore.ops.glu(hidden_states, axis=1)
        # hidden_states = hidden_states.transpose(1, 2) # -> T x B x (C x D)
        hidden_states = hidden_states.swapaxes(1,2)
        return hidden_states

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextAttention

Bases: Module

Multi-headed attention from 'Attention Is All You Need' paper

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
class Speech2TextAttention(nn.Module):
    """Multi-headed attention from 'Attention Is All You Need' paper"""

    def __init__(
        self,
        embed_dim: int,
        num_heads: int,
        dropout: float = 0.0,
        is_decoder: bool = False,
        bias: bool = True,
        is_causal: bool = False,
        config: Optional[Speech2TextConfig] = None,
    ):
        super().__init__()
        self.embed_dim = embed_dim
        self.num_heads = num_heads
        self.dropout = dropout
        self.head_dim = embed_dim // num_heads
        self.config = config

        if (self.head_dim * num_heads) != self.embed_dim:
            raise ValueError(
                f"embed_dim must be divisible by num_heads (got `embed_dim`: {self.embed_dim}"
                f" and `num_heads`: {num_heads})."
            )
        self.scaling = self.head_dim**-0.5
        self.is_decoder = is_decoder
        self.is_causal = is_causal

        self.k_proj = nn.Linear(embed_dim, embed_dim, bias=bias)
        self.v_proj = nn.Linear(embed_dim, embed_dim, bias=bias)
        self.q_proj = nn.Linear(embed_dim, embed_dim, bias=bias)
        self.out_proj = nn.Linear(embed_dim, embed_dim, bias=bias)

    def _shape(self, tensor: mindspore.Tensor, seq_len: int, bsz: int):
        return tensor.view(bsz, seq_len, self.num_heads, self.head_dim).swapaxes(1, 2)

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        key_value_states: Optional[mindspore.Tensor] = None,
        past_key_value: Optional[Tuple[mindspore.Tensor]] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        layer_head_mask: Optional[mindspore.Tensor] = None,
        output_attentions: bool = False,
    ) -> Tuple[mindspore.Tensor, Optional[mindspore.Tensor], Optional[Tuple[mindspore.Tensor]]]:
        """Input shape: Batch x Time x Channel"""

        # if key_value_states are provided this layer is used as a cross-attention layer
        # for the decoder
        is_cross_attention = key_value_states is not None

        bsz, tgt_len, _ = hidden_states.shape

        # get query proj
        query_states = self.q_proj(hidden_states) * self.scaling
        # get key, value proj
        # `past_key_value[0].shape[2] == key_value_states.shape[1]`
        # is checking that the `sequence_length` of the `past_key_value` is the same as
        # the provided `key_value_states` to support prefix tuning
        if (
            is_cross_attention
            and past_key_value is not None
            and past_key_value[0].shape[2] == key_value_states.shape[1]
        ):
            # reuse k,v, cross_attentions
            key_states = past_key_value[0]
            value_states = past_key_value[1]
        elif is_cross_attention:
            # cross_attentions
            key_states = self._shape(self.k_proj(key_value_states), -1, bsz)
            value_states = self._shape(self.v_proj(key_value_states), -1, bsz)
        elif past_key_value is not None:
            # reuse k, v, self_attention
            key_states = self._shape(self.k_proj(hidden_states), -1, bsz)
            value_states = self._shape(self.v_proj(hidden_states), -1, bsz)
            key_states = ops.cat([past_key_value[0], key_states], axis=2)
            value_states = ops.cat([past_key_value[1], value_states], axis=2)
        else:
            # self_attention
            key_states = self._shape(self.k_proj(hidden_states), -1, bsz)
            value_states = self._shape(self.v_proj(hidden_states), -1, bsz)

        if self.is_decoder:
            # if cross_attention save Tuple(mindspore.Tensor, mindspore.Tensor) of all cross attention key/value_states.
            # Further calls to cross_attention layer can then reuse all cross-attention
            # key/value_states (first "if" case)
            # if uni-directional self-attention (decoder) save Tuple(mindspore.Tensor, mindspore.Tensor) of
            # all previous decoder key/value_states. Further calls to uni-directional self-attention
            # can concat previous decoder key/value_states to current projected key/value_states (third "elif" case)
            # if encoder bi-directional self-attention `past_key_value` is always `None`
            past_key_value = (key_states, value_states)

        proj_shape = (bsz * self.num_heads, -1, self.head_dim)
        query_states = self._shape(query_states, tgt_len, bsz).view(*proj_shape)
        key_states = key_states.reshape(*proj_shape)
        value_states = value_states.reshape(*proj_shape)

        src_len = key_states.shape[1]
        attn_weights = ops.bmm(query_states, key_states.swapaxes(1, 2))

        if attn_weights.shape != (bsz * self.num_heads, tgt_len, src_len):
            raise ValueError(
                f"Attention weights should be of size {(bsz * self.num_heads, tgt_len, src_len)}, but is"
                f" {attn_weights.shape}"
            )

        if attention_mask is not None:
            if attention_mask.shape != (bsz, 1, tgt_len, src_len):
                raise ValueError(
                    f"Attention mask should be of size {(bsz, 1, tgt_len, src_len)}, but is {attention_mask.shape}"
                )
            attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) + attention_mask
            attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

        attn_weights = mindspore.ops.softmax(attn_weights, axis=-1)

        if layer_head_mask is not None:
            if layer_head_mask.shape != (self.num_heads,):
                raise ValueError(
                    f"Head mask for a single layer should be of size {(self.num_heads,)}, but is"
                    f" {layer_head_mask.shape}"
                )
            attn_weights = layer_head_mask.view(1, -1, 1, 1) * attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
            attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

        if output_attentions:
            # this operation is a bit awkward, but it's required to
            # make sure that attn_weights keeps its gradient.
            # In order to do so, attn_weights have to be reshaped
            # twice and have to be reused in the following
            attn_weights_reshaped = attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
            attn_weights = attn_weights_reshaped.view(bsz * self.num_heads, tgt_len, src_len)
        else:
            attn_weights_reshaped = None

        attn_probs = mindspore.ops.dropout(attn_weights, p=self.dropout, training=self.training)

        attn_output = ops.bmm(attn_probs, value_states)

        if attn_output.shape != (bsz * self.num_heads, tgt_len, self.head_dim):
            raise ValueError(
                f"`attn_output` should be of size {(bsz * self.num_heads, tgt_len, self.head_dim)}, but is"
                f" {attn_output.shape}"
            )

        attn_output = attn_output.view(bsz, self.num_heads, tgt_len, self.head_dim)
        attn_output = attn_output.swapaxes(1, 2)

        # Use the `embed_dim` from the config (stored in the class) rather than `hidden_state` because `attn_output` can be
        # partitioned across GPUs when using tensor-parallelism.
        attn_output = attn_output.reshape(bsz, tgt_len, self.embed_dim)

        attn_output = self.out_proj(attn_output)

        return attn_output, attn_weights_reshaped, past_key_value

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextAttention.forward(hidden_states, key_value_states=None, past_key_value=None, attention_mask=None, layer_head_mask=None, output_attentions=False)

Input shape: Batch x Time x Channel

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
def forward(
    self,
    hidden_states: mindspore.Tensor,
    key_value_states: Optional[mindspore.Tensor] = None,
    past_key_value: Optional[Tuple[mindspore.Tensor]] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    layer_head_mask: Optional[mindspore.Tensor] = None,
    output_attentions: bool = False,
) -> Tuple[mindspore.Tensor, Optional[mindspore.Tensor], Optional[Tuple[mindspore.Tensor]]]:
    """Input shape: Batch x Time x Channel"""

    # if key_value_states are provided this layer is used as a cross-attention layer
    # for the decoder
    is_cross_attention = key_value_states is not None

    bsz, tgt_len, _ = hidden_states.shape

    # get query proj
    query_states = self.q_proj(hidden_states) * self.scaling
    # get key, value proj
    # `past_key_value[0].shape[2] == key_value_states.shape[1]`
    # is checking that the `sequence_length` of the `past_key_value` is the same as
    # the provided `key_value_states` to support prefix tuning
    if (
        is_cross_attention
        and past_key_value is not None
        and past_key_value[0].shape[2] == key_value_states.shape[1]
    ):
        # reuse k,v, cross_attentions
        key_states = past_key_value[0]
        value_states = past_key_value[1]
    elif is_cross_attention:
        # cross_attentions
        key_states = self._shape(self.k_proj(key_value_states), -1, bsz)
        value_states = self._shape(self.v_proj(key_value_states), -1, bsz)
    elif past_key_value is not None:
        # reuse k, v, self_attention
        key_states = self._shape(self.k_proj(hidden_states), -1, bsz)
        value_states = self._shape(self.v_proj(hidden_states), -1, bsz)
        key_states = ops.cat([past_key_value[0], key_states], axis=2)
        value_states = ops.cat([past_key_value[1], value_states], axis=2)
    else:
        # self_attention
        key_states = self._shape(self.k_proj(hidden_states), -1, bsz)
        value_states = self._shape(self.v_proj(hidden_states), -1, bsz)

    if self.is_decoder:
        # if cross_attention save Tuple(mindspore.Tensor, mindspore.Tensor) of all cross attention key/value_states.
        # Further calls to cross_attention layer can then reuse all cross-attention
        # key/value_states (first "if" case)
        # if uni-directional self-attention (decoder) save Tuple(mindspore.Tensor, mindspore.Tensor) of
        # all previous decoder key/value_states. Further calls to uni-directional self-attention
        # can concat previous decoder key/value_states to current projected key/value_states (third "elif" case)
        # if encoder bi-directional self-attention `past_key_value` is always `None`
        past_key_value = (key_states, value_states)

    proj_shape = (bsz * self.num_heads, -1, self.head_dim)
    query_states = self._shape(query_states, tgt_len, bsz).view(*proj_shape)
    key_states = key_states.reshape(*proj_shape)
    value_states = value_states.reshape(*proj_shape)

    src_len = key_states.shape[1]
    attn_weights = ops.bmm(query_states, key_states.swapaxes(1, 2))

    if attn_weights.shape != (bsz * self.num_heads, tgt_len, src_len):
        raise ValueError(
            f"Attention weights should be of size {(bsz * self.num_heads, tgt_len, src_len)}, but is"
            f" {attn_weights.shape}"
        )

    if attention_mask is not None:
        if attention_mask.shape != (bsz, 1, tgt_len, src_len):
            raise ValueError(
                f"Attention mask should be of size {(bsz, 1, tgt_len, src_len)}, but is {attention_mask.shape}"
            )
        attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) + attention_mask
        attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

    attn_weights = mindspore.ops.softmax(attn_weights, axis=-1)

    if layer_head_mask is not None:
        if layer_head_mask.shape != (self.num_heads,):
            raise ValueError(
                f"Head mask for a single layer should be of size {(self.num_heads,)}, but is"
                f" {layer_head_mask.shape}"
            )
        attn_weights = layer_head_mask.view(1, -1, 1, 1) * attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
        attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

    if output_attentions:
        # this operation is a bit awkward, but it's required to
        # make sure that attn_weights keeps its gradient.
        # In order to do so, attn_weights have to be reshaped
        # twice and have to be reused in the following
        attn_weights_reshaped = attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
        attn_weights = attn_weights_reshaped.view(bsz * self.num_heads, tgt_len, src_len)
    else:
        attn_weights_reshaped = None

    attn_probs = mindspore.ops.dropout(attn_weights, p=self.dropout, training=self.training)

    attn_output = ops.bmm(attn_probs, value_states)

    if attn_output.shape != (bsz * self.num_heads, tgt_len, self.head_dim):
        raise ValueError(
            f"`attn_output` should be of size {(bsz * self.num_heads, tgt_len, self.head_dim)}, but is"
            f" {attn_output.shape}"
        )

    attn_output = attn_output.view(bsz, self.num_heads, tgt_len, self.head_dim)
    attn_output = attn_output.swapaxes(1, 2)

    # Use the `embed_dim` from the config (stored in the class) rather than `hidden_state` because `attn_output` can be
    # partitioned across GPUs when using tensor-parallelism.
    attn_output = attn_output.reshape(bsz, tgt_len, self.embed_dim)

    attn_output = self.out_proj(attn_output)

    return attn_output, attn_weights_reshaped, past_key_value

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextDecoder

Bases: Speech2TextPreTrainedModel

Transformer decoder consisting of config.decoder_layers layers. Each layer is a [Speech2TextDecoderLayer]

PARAMETER DESCRIPTION
config

Speech2TextConfig

TYPE: Speech2TextConfig

embed_tokens

output embedding

TYPE: Embedding

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
class Speech2TextDecoder(Speech2TextPreTrainedModel):
    """
    Transformer decoder consisting of *config.decoder_layers* layers. Each layer is a [`Speech2TextDecoderLayer`]

    Args:
        config: Speech2TextConfig
        embed_tokens (nn.Embedding): output embedding
    """

    def __init__(self, config: Speech2TextConfig):
        super().__init__(config)
        self.dropout = config.dropout
        self.layerdrop = config.decoder_layerdrop
        self.padding_idx = config.pad_token_id
        self.max_target_positions = config.max_target_positions
        self.embed_scale = math.sqrt(config.d_model) if config.scale_embedding else 1.0

        self.embed_tokens = nn.Embedding(config.vocab_size, config.d_model, self.padding_idx)

        self.embed_positions = Speech2TextSinusoidalPositionalEmbedding(
            self.max_target_positions,
            config.d_model,
            self.padding_idx,
        )

        self.layers = nn.ModuleList([Speech2TextDecoderLayer(config) for _ in range(config.decoder_layers)])

        self.layer_norm = nn.LayerNorm(config.d_model)

        self.gradient_checkpointing = False
        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.embed_tokens

    def set_input_embeddings(self, value):
        self.embed_tokens = value

    def forward(
        self,
        input_ids=None,
        attention_mask=None,
        encoder_hidden_states=None,
        encoder_attention_mask=None,
        head_mask=None,
        cross_attn_head_mask=None,
        past_key_values=None,
        inputs_embeds=None,
        use_cache=None,
        output_attentions=None,
        output_hidden_states=None,
        return_dict=None,
    ):
        r"""
        Args:
            input_ids (`mindspore.Tensor` of shape `(batch_size, sequence_length)`):
                Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you
                provide it.

                Indices can be obtained using [`Speech2TextTokenizer`]. See [`PreTrainedTokenizer.encode`] and
                [`PreTrainedTokenizer.__call__`] for details.

                [What are input IDs?](../glossary#input-ids)
            attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            encoder_hidden_states (`mindspore.Tensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*):
                Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
                of the decoder.
            encoder_attention_mask (`mindspore.Tensor` of shape `(batch_size, encoder_sequence_length)`, *optional*):
                Mask to avoid performing cross-attention on padding tokens indices of encoder input_ids. Mask values
                selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            head_mask (`mindspore.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*):
                Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`:

                - 1 indicates the head is **not masked**,
                - 0 indicates the head is **masked**.

            cross_attn_head_mask (`mindspore.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*):
                Mask to nullify selected heads of the attention modules in encoder to avoid performing cross-attention
                on hidden heads. Mask values selected in `[0, 1]`:

                - 1 indicates the head is **not masked**,
                - 0 indicates the head is **masked**.

            past_key_values (`tuple(tuple(mindspore.Tensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
                Tuple of `tuple(mindspore.Tensor)` of length `config.n_layers`, with each tuple having 2 tensors of
                shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of
                shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

                Contains pre-computed hidden-states (key and values in the self-attention blocks and in the
                cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.

                If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those
                that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of
                all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
            inputs_embeds (`mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
                Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
                This is useful if you want more control over how to convert `input_ids` indices into associated vectors
                than the model's internal embedding lookup matrix.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            output_hidden_states (`bool`, *optional*):
                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
                for more detail.
            return_dict (`bool`, *optional*):
                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        # retrieve input_ids and inputs_embeds
        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time")
        elif input_ids is not None:
            input_shape = input_ids.shape
            input_ids = input_ids.view(-1, input_shape[-1])
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.shape[:-1]
        else:
            raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")

        # past_key_values_length
        past_key_values_length = past_key_values[0][0].shape[2] if past_key_values is not None else 0

        if inputs_embeds is None:
            inputs_embeds = self.embed_tokens(input_ids) * self.embed_scale

        attention_mask = _prepare_4d_causal_attention_mask(
            attention_mask, input_shape, inputs_embeds, past_key_values_length
        )

        # expand encoder attention mask
        if encoder_hidden_states is not None and encoder_attention_mask is not None:
            # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
            encoder_attention_mask = _prepare_4d_attention_mask(
                encoder_attention_mask, inputs_embeds.dtype, tgt_len=input_shape[-1]
            )

        # embed positions
        positions = self.embed_positions(input_ids, past_key_values_length=past_key_values_length)

        hidden_states = inputs_embeds + positions
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)

        if self.gradient_checkpointing and self.training:
            if use_cache:
                logger.warning_once(
                    "`use_cache = True` is incompatible with gradient checkpointing. Setting `use_cache = False`..."
                )
                use_cache = False

        # decoder layers
        all_hidden_states = () if output_hidden_states else None
        all_self_attns = () if output_attentions else None
        all_cross_attentions = () if (output_attentions and encoder_hidden_states is not None) else None
        next_decoder_cache = () if use_cache else None

        # check if head_mask/cross_attn_head_mask has a correct number of layers specified if desired
        for attn_mask, mask_name in zip([head_mask, cross_attn_head_mask], ["head_mask", "cross_attn_head_mask"]):
            if attn_mask is not None:
                assert attn_mask.shape[0] == (len(self.layers)), (
                    f"The `{mask_name}` should be specified for {len(self.layers)} layers, but it is for"
                    f" {head_mask.shape[0]}."
                )
        for idx, decoder_layer in enumerate(self.layers):
            # add LayerDrop (see https://arxiv.org/abs/1909.11556 for description)
            if output_hidden_states:
                all_hidden_states += (hidden_states,)
            if self.training:
                dropout_probability = ops.rand([])
                if dropout_probability < self.layerdrop:
                    continue

            past_key_value = past_key_values[idx] if past_key_values is not None else None

            if self.gradient_checkpointing and self.training:
                layer_outputs = self._gradient_checkpointing_func(
                    decoder_layer.__call__,
                    hidden_states,
                    attention_mask,
                    encoder_hidden_states,
                    encoder_attention_mask,
                    head_mask[idx] if head_mask is not None else None,
                    cross_attn_head_mask[idx] if cross_attn_head_mask is not None else None,
                    None,
                    output_attentions,
                    use_cache,
                )
            else:
                layer_outputs = decoder_layer(
                    hidden_states,
                    attention_mask=attention_mask,
                    encoder_hidden_states=encoder_hidden_states,
                    encoder_attention_mask=encoder_attention_mask,
                    layer_head_mask=(head_mask[idx] if head_mask is not None else None),
                    cross_attn_layer_head_mask=(
                        cross_attn_head_mask[idx] if cross_attn_head_mask is not None else None
                    ),
                    past_key_value=past_key_value,
                    output_attentions=output_attentions,
                    use_cache=use_cache,
                )
            hidden_states = layer_outputs[0]

            if use_cache:
                next_decoder_cache += (layer_outputs[3 if output_attentions else 1],)

            if output_attentions:
                all_self_attns += (layer_outputs[1],)

                if encoder_hidden_states is not None:
                    all_cross_attentions += (layer_outputs[2],)

        hidden_states = self.layer_norm(hidden_states)
        # add hidden states from the last decoder layer
        if output_hidden_states:
            all_hidden_states += (hidden_states,)

        next_cache = next_decoder_cache if use_cache else None
        if not return_dict:
            return tuple(
                v
                for v in [hidden_states, next_cache, all_hidden_states, all_self_attns, all_cross_attentions]
                if v is not None
            )
        return BaseModelOutputWithPastAndCrossAttentions(
            last_hidden_state=hidden_states,
            past_key_values=next_cache,
            hidden_states=all_hidden_states,
            attentions=all_self_attns,
            cross_attentions=all_cross_attentions,
        )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextDecoder.forward(input_ids=None, attention_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, head_mask=None, cross_attn_head_mask=None, past_key_values=None, inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
input_ids

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using [Speech2TextTokenizer]. See [PreTrainedTokenizer.encode] and [PreTrainedTokenizer.__call__] for details.

What are input IDs?

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)` DEFAULT: None

attention_mask

Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

What are attention masks?

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

encoder_hidden_states

Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.

TYPE: `mindspore.Tensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional* DEFAULT: None

encoder_attention_mask

Mask to avoid performing cross-attention on padding tokens indices of encoder input_ids. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

What are attention masks?

TYPE: `mindspore.Tensor` of shape `(batch_size, encoder_sequence_length)`, *optional* DEFAULT: None

head_mask

Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]:

  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.

TYPE: `mindspore.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional* DEFAULT: None

cross_attn_head_mask

Mask to nullify selected heads of the attention modules in encoder to avoid performing cross-attention on hidden heads. Mask values selected in [0, 1]:

  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.

TYPE: `mindspore.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional* DEFAULT: None

past_key_values

Tuple of tuple(mindspore.Tensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don't have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

TYPE: `tuple(tuple(mindspore.Tensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True` DEFAULT: None

inputs_embeds

Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional* DEFAULT: None

output_attentions

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: None

output_hidden_states

Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: None

return_dict

Whether or not to return a [~utils.ModelOutput] instead of a plain tuple.

TYPE: `bool`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
def forward(
    self,
    input_ids=None,
    attention_mask=None,
    encoder_hidden_states=None,
    encoder_attention_mask=None,
    head_mask=None,
    cross_attn_head_mask=None,
    past_key_values=None,
    inputs_embeds=None,
    use_cache=None,
    output_attentions=None,
    output_hidden_states=None,
    return_dict=None,
):
    r"""
    Args:
        input_ids (`mindspore.Tensor` of shape `(batch_size, sequence_length)`):
            Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you
            provide it.

            Indices can be obtained using [`Speech2TextTokenizer`]. See [`PreTrainedTokenizer.encode`] and
            [`PreTrainedTokenizer.__call__`] for details.

            [What are input IDs?](../glossary#input-ids)
        attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.

            [What are attention masks?](../glossary#attention-mask)
        encoder_hidden_states (`mindspore.Tensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
            of the decoder.
        encoder_attention_mask (`mindspore.Tensor` of shape `(batch_size, encoder_sequence_length)`, *optional*):
            Mask to avoid performing cross-attention on padding tokens indices of encoder input_ids. Mask values
            selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.

            [What are attention masks?](../glossary#attention-mask)
        head_mask (`mindspore.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*):
            Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`:

            - 1 indicates the head is **not masked**,
            - 0 indicates the head is **masked**.

        cross_attn_head_mask (`mindspore.Tensor` of shape `(decoder_layers, decoder_attention_heads)`, *optional*):
            Mask to nullify selected heads of the attention modules in encoder to avoid performing cross-attention
            on hidden heads. Mask values selected in `[0, 1]`:

            - 1 indicates the head is **not masked**,
            - 0 indicates the head is **masked**.

        past_key_values (`tuple(tuple(mindspore.Tensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
            Tuple of `tuple(mindspore.Tensor)` of length `config.n_layers`, with each tuple having 2 tensors of
            shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of
            shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

            Contains pre-computed hidden-states (key and values in the self-attention blocks and in the
            cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.

            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those
            that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of
            all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        inputs_embeds (`mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
            This is useful if you want more control over how to convert `input_ids` indices into associated vectors
            than the model's internal embedding lookup matrix.
        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
        output_hidden_states (`bool`, *optional*):
            Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
            for more detail.
        return_dict (`bool`, *optional*):
            Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
    """
    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    use_cache = use_cache if use_cache is not None else self.config.use_cache
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    # retrieve input_ids and inputs_embeds
    if input_ids is not None and inputs_embeds is not None:
        raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time")
    elif input_ids is not None:
        input_shape = input_ids.shape
        input_ids = input_ids.view(-1, input_shape[-1])
    elif inputs_embeds is not None:
        input_shape = inputs_embeds.shape[:-1]
    else:
        raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")

    # past_key_values_length
    past_key_values_length = past_key_values[0][0].shape[2] if past_key_values is not None else 0

    if inputs_embeds is None:
        inputs_embeds = self.embed_tokens(input_ids) * self.embed_scale

    attention_mask = _prepare_4d_causal_attention_mask(
        attention_mask, input_shape, inputs_embeds, past_key_values_length
    )

    # expand encoder attention mask
    if encoder_hidden_states is not None and encoder_attention_mask is not None:
        # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
        encoder_attention_mask = _prepare_4d_attention_mask(
            encoder_attention_mask, inputs_embeds.dtype, tgt_len=input_shape[-1]
        )

    # embed positions
    positions = self.embed_positions(input_ids, past_key_values_length=past_key_values_length)

    hidden_states = inputs_embeds + positions
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)

    if self.gradient_checkpointing and self.training:
        if use_cache:
            logger.warning_once(
                "`use_cache = True` is incompatible with gradient checkpointing. Setting `use_cache = False`..."
            )
            use_cache = False

    # decoder layers
    all_hidden_states = () if output_hidden_states else None
    all_self_attns = () if output_attentions else None
    all_cross_attentions = () if (output_attentions and encoder_hidden_states is not None) else None
    next_decoder_cache = () if use_cache else None

    # check if head_mask/cross_attn_head_mask has a correct number of layers specified if desired
    for attn_mask, mask_name in zip([head_mask, cross_attn_head_mask], ["head_mask", "cross_attn_head_mask"]):
        if attn_mask is not None:
            assert attn_mask.shape[0] == (len(self.layers)), (
                f"The `{mask_name}` should be specified for {len(self.layers)} layers, but it is for"
                f" {head_mask.shape[0]}."
            )
    for idx, decoder_layer in enumerate(self.layers):
        # add LayerDrop (see https://arxiv.org/abs/1909.11556 for description)
        if output_hidden_states:
            all_hidden_states += (hidden_states,)
        if self.training:
            dropout_probability = ops.rand([])
            if dropout_probability < self.layerdrop:
                continue

        past_key_value = past_key_values[idx] if past_key_values is not None else None

        if self.gradient_checkpointing and self.training:
            layer_outputs = self._gradient_checkpointing_func(
                decoder_layer.__call__,
                hidden_states,
                attention_mask,
                encoder_hidden_states,
                encoder_attention_mask,
                head_mask[idx] if head_mask is not None else None,
                cross_attn_head_mask[idx] if cross_attn_head_mask is not None else None,
                None,
                output_attentions,
                use_cache,
            )
        else:
            layer_outputs = decoder_layer(
                hidden_states,
                attention_mask=attention_mask,
                encoder_hidden_states=encoder_hidden_states,
                encoder_attention_mask=encoder_attention_mask,
                layer_head_mask=(head_mask[idx] if head_mask is not None else None),
                cross_attn_layer_head_mask=(
                    cross_attn_head_mask[idx] if cross_attn_head_mask is not None else None
                ),
                past_key_value=past_key_value,
                output_attentions=output_attentions,
                use_cache=use_cache,
            )
        hidden_states = layer_outputs[0]

        if use_cache:
            next_decoder_cache += (layer_outputs[3 if output_attentions else 1],)

        if output_attentions:
            all_self_attns += (layer_outputs[1],)

            if encoder_hidden_states is not None:
                all_cross_attentions += (layer_outputs[2],)

    hidden_states = self.layer_norm(hidden_states)
    # add hidden states from the last decoder layer
    if output_hidden_states:
        all_hidden_states += (hidden_states,)

    next_cache = next_decoder_cache if use_cache else None
    if not return_dict:
        return tuple(
            v
            for v in [hidden_states, next_cache, all_hidden_states, all_self_attns, all_cross_attentions]
            if v is not None
        )
    return BaseModelOutputWithPastAndCrossAttentions(
        last_hidden_state=hidden_states,
        past_key_values=next_cache,
        hidden_states=all_hidden_states,
        attentions=all_self_attns,
        cross_attentions=all_cross_attentions,
    )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextDecoderLayer

Bases: Module

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
class Speech2TextDecoderLayer(nn.Module):
    def __init__(self, config: Speech2TextConfig):
        super().__init__()
        self.embed_dim = config.d_model

        self.self_attn = SPEECH_TO_TEXT_ATTENTION_CLASSES[config._attn_implementation](
            embed_dim=self.embed_dim,
            num_heads=config.decoder_attention_heads,
            dropout=config.attention_dropout,
            is_decoder=True,
            is_causal=True,
            config=config,
        )
        self.dropout = config.dropout
        self.activation_fn = ACT2FN[config.activation_function]
        self.activation_dropout = config.activation_dropout

        self.self_attn_layer_norm = nn.LayerNorm(self.embed_dim)
        self.encoder_attn = SPEECH_TO_TEXT_ATTENTION_CLASSES[config._attn_implementation](
            self.embed_dim,
            config.decoder_attention_heads,
            dropout=config.attention_dropout,
            is_decoder=True,
            config=config,
        )
        self.encoder_attn_layer_norm = nn.LayerNorm(self.embed_dim)
        self.fc1 = nn.Linear(self.embed_dim, config.decoder_ffn_dim)
        self.fc2 = nn.Linear(config.decoder_ffn_dim, self.embed_dim)
        self.final_layer_norm = nn.LayerNorm(self.embed_dim)

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        attention_mask: Optional[mindspore.Tensor] = None,
        encoder_hidden_states: Optional[mindspore.Tensor] = None,
        encoder_attention_mask: Optional[mindspore.Tensor] = None,
        layer_head_mask: Optional[mindspore.Tensor] = None,
        cross_attn_layer_head_mask: Optional[mindspore.Tensor] = None,
        past_key_value: Optional[Tuple[mindspore.Tensor]] = None,
        output_attentions: Optional[bool] = False,
        use_cache: Optional[bool] = True,
    ) -> mindspore.Tensor:
        """
        Args:
            hidden_states (`mindspore.Tensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`mindspore.Tensor`): attention mask of size
                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
            encoder_hidden_states (`mindspore.Tensor`):
                cross attention input to the layer of shape `(batch, seq_len, embed_dim)`
            encoder_attention_mask (`mindspore.Tensor`): encoder attention mask of size
                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
            layer_head_mask (`mindspore.Tensor`): mask for attention heads in a given layer of size
                `(encoder_attention_heads,)`.
            cross_attn_layer_head_mask (`mindspore.Tensor`): mask for cross-attention heads in a given layer of
                size `(decoder_attention_heads,)`.
            past_key_value (`Tuple(mindspore.Tensor)`): cached past key and value projection states
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
        """
        residual = hidden_states
        hidden_states = self.self_attn_layer_norm(hidden_states)

        # Self Attention
        # decoder uni-directional self-attention cached key/values tuple is at positions 1,2
        self_attn_past_key_value = past_key_value[:2] if past_key_value is not None else None
        # add present self-attn cache to positions 1,2 of present_key_value tuple
        hidden_states, self_attn_weights, present_key_value = self.self_attn(
            hidden_states=hidden_states,
            past_key_value=self_attn_past_key_value,
            attention_mask=attention_mask,
            layer_head_mask=layer_head_mask,
            output_attentions=output_attentions,
        )
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
        hidden_states = residual + hidden_states

        # Cross-Attention Block
        cross_attn_present_key_value = None
        cross_attn_weights = None
        if encoder_hidden_states is not None:
            residual = hidden_states
            hidden_states = self.encoder_attn_layer_norm(hidden_states)

            # cross_attn cached key/values tuple is at positions 3,4 of present_key_value tuple
            cross_attn_past_key_value = past_key_value[-2:] if past_key_value is not None else None
            hidden_states, cross_attn_weights, cross_attn_present_key_value = self.encoder_attn(
                hidden_states=hidden_states,
                key_value_states=encoder_hidden_states,
                attention_mask=encoder_attention_mask,
                layer_head_mask=cross_attn_layer_head_mask,
                past_key_value=cross_attn_past_key_value,
                output_attentions=output_attentions,
            )
            hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
            hidden_states = residual + hidden_states

            # add cross-attn to positions 3,4 of present_key_value tuple
            present_key_value = present_key_value + cross_attn_present_key_value

        # Fully Connected
        residual = hidden_states
        hidden_states = self.final_layer_norm(hidden_states)
        hidden_states = self.activation_fn(self.fc1(hidden_states))
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.activation_dropout, training=self.training)
        hidden_states = self.fc2(hidden_states)
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
        hidden_states = residual + hidden_states

        outputs = (hidden_states,)

        if output_attentions:
            outputs += (self_attn_weights, cross_attn_weights)

        if use_cache:
            outputs += (present_key_value,)

        return outputs

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextDecoderLayer.forward(hidden_states, attention_mask=None, encoder_hidden_states=None, encoder_attention_mask=None, layer_head_mask=None, cross_attn_layer_head_mask=None, past_key_value=None, output_attentions=False, use_cache=True)

PARAMETER DESCRIPTION
hidden_states

input to the layer of shape (batch, seq_len, embed_dim)

TYPE: `mindspore.Tensor`

attention_mask

attention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.

TYPE: `mindspore.Tensor` DEFAULT: None

encoder_hidden_states

cross attention input to the layer of shape (batch, seq_len, embed_dim)

TYPE: `mindspore.Tensor` DEFAULT: None

encoder_attention_mask

encoder attention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.

TYPE: `mindspore.Tensor` DEFAULT: None

layer_head_mask

mask for attention heads in a given layer of size (encoder_attention_heads,).

TYPE: `mindspore.Tensor` DEFAULT: None

cross_attn_layer_head_mask

mask for cross-attention heads in a given layer of size (decoder_attention_heads,).

TYPE: `mindspore.Tensor` DEFAULT: None

past_key_value

cached past key and value projection states

TYPE: `Tuple(mindspore.Tensor)` DEFAULT: None

output_attentions

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: False

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
def forward(
    self,
    hidden_states: mindspore.Tensor,
    attention_mask: Optional[mindspore.Tensor] = None,
    encoder_hidden_states: Optional[mindspore.Tensor] = None,
    encoder_attention_mask: Optional[mindspore.Tensor] = None,
    layer_head_mask: Optional[mindspore.Tensor] = None,
    cross_attn_layer_head_mask: Optional[mindspore.Tensor] = None,
    past_key_value: Optional[Tuple[mindspore.Tensor]] = None,
    output_attentions: Optional[bool] = False,
    use_cache: Optional[bool] = True,
) -> mindspore.Tensor:
    """
    Args:
        hidden_states (`mindspore.Tensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
        attention_mask (`mindspore.Tensor`): attention mask of size
            `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
        encoder_hidden_states (`mindspore.Tensor`):
            cross attention input to the layer of shape `(batch, seq_len, embed_dim)`
        encoder_attention_mask (`mindspore.Tensor`): encoder attention mask of size
            `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
        layer_head_mask (`mindspore.Tensor`): mask for attention heads in a given layer of size
            `(encoder_attention_heads,)`.
        cross_attn_layer_head_mask (`mindspore.Tensor`): mask for cross-attention heads in a given layer of
            size `(decoder_attention_heads,)`.
        past_key_value (`Tuple(mindspore.Tensor)`): cached past key and value projection states
        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
    """
    residual = hidden_states
    hidden_states = self.self_attn_layer_norm(hidden_states)

    # Self Attention
    # decoder uni-directional self-attention cached key/values tuple is at positions 1,2
    self_attn_past_key_value = past_key_value[:2] if past_key_value is not None else None
    # add present self-attn cache to positions 1,2 of present_key_value tuple
    hidden_states, self_attn_weights, present_key_value = self.self_attn(
        hidden_states=hidden_states,
        past_key_value=self_attn_past_key_value,
        attention_mask=attention_mask,
        layer_head_mask=layer_head_mask,
        output_attentions=output_attentions,
    )
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
    hidden_states = residual + hidden_states

    # Cross-Attention Block
    cross_attn_present_key_value = None
    cross_attn_weights = None
    if encoder_hidden_states is not None:
        residual = hidden_states
        hidden_states = self.encoder_attn_layer_norm(hidden_states)

        # cross_attn cached key/values tuple is at positions 3,4 of present_key_value tuple
        cross_attn_past_key_value = past_key_value[-2:] if past_key_value is not None else None
        hidden_states, cross_attn_weights, cross_attn_present_key_value = self.encoder_attn(
            hidden_states=hidden_states,
            key_value_states=encoder_hidden_states,
            attention_mask=encoder_attention_mask,
            layer_head_mask=cross_attn_layer_head_mask,
            past_key_value=cross_attn_past_key_value,
            output_attentions=output_attentions,
        )
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
        hidden_states = residual + hidden_states

        # add cross-attn to positions 3,4 of present_key_value tuple
        present_key_value = present_key_value + cross_attn_present_key_value

    # Fully Connected
    residual = hidden_states
    hidden_states = self.final_layer_norm(hidden_states)
    hidden_states = self.activation_fn(self.fc1(hidden_states))
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.activation_dropout, training=self.training)
    hidden_states = self.fc2(hidden_states)
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
    hidden_states = residual + hidden_states

    outputs = (hidden_states,)

    if output_attentions:
        outputs += (self_attn_weights, cross_attn_weights)

    if use_cache:
        outputs += (present_key_value,)

    return outputs

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextEncoder

Bases: Speech2TextPreTrainedModel

Transformer encoder consisting of config.encoder_layers self attention layers. Each layer is a [Speech2TextEncoderLayer].

PARAMETER DESCRIPTION
config

Speech2TextConfig

TYPE: Speech2TextConfig

embed_tokens

output embedding

TYPE: Embedding

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
class Speech2TextEncoder(Speech2TextPreTrainedModel):
    """
    Transformer encoder consisting of *config.encoder_layers* self attention layers. Each layer is a
    [`Speech2TextEncoderLayer`].

    Args:
        config: Speech2TextConfig
        embed_tokens (nn.Embedding): output embedding
    """

    def __init__(self, config: Speech2TextConfig):
        super().__init__(config)

        self.dropout = config.dropout
        self.layerdrop = config.encoder_layerdrop

        embed_dim = config.d_model
        self.padding_idx = config.pad_token_id
        self.max_source_positions = config.max_source_positions
        self.embed_scale = math.sqrt(embed_dim) if config.scale_embedding else 1.0

        self.conv = Conv1dSubsampler(config)

        self.embed_positions = Speech2TextSinusoidalPositionalEmbedding(
            self.max_source_positions,
            embed_dim,
            self.padding_idx,
        )
        self.layers = nn.ModuleList([Speech2TextEncoderLayer(config) for _ in range(config.encoder_layers)])
        self.layer_norm = nn.LayerNorm(config.d_model)

        self.gradient_checkpointing = False
        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_features,
        attention_mask=None,
        head_mask=None,
        output_attentions=None,
        output_hidden_states=None,
        return_dict=None,
    ):
        r"""
        Args:
            input_features (`mindspore.Tensor` of shape `(batch_size, sequence_length, feature_size)`):
                Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be
                obtained by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a
                `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into
                `input_features`, the [`AutoFeatureExtractor`] should be used for extracting the fbank features,
                padding and conversion into a tensor of type `mindspore.Tensor`. See
                [`~Speech2TextFeatureExtractor.__call__`]
            attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing convolution and attention on padding token indices. Mask values selected in
                `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            head_mask (`mindspore.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*):
                Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`:

                - 1 indicates the head is **not masked**,
                - 0 indicates the head is **masked**.

            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            output_hidden_states (`bool`, *optional*):
                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
                for more detail.
            return_dict (`bool`, *optional*):
                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
        inputs_embeds = self.conv(input_features)
        inputs_embeds = self.embed_scale * inputs_embeds

        # subsample attention mask if necessary
        if attention_mask is not None:
            attention_mask = self._get_feature_vector_attention_mask(inputs_embeds.shape[1], attention_mask)
            padding_mask = attention_mask.ne(1).long()
        else:
            padding_mask = ops.zeros(inputs_embeds.shape[:2], dtype=mstype.long)

        embed_pos = self.embed_positions(padding_mask)

        hidden_states = inputs_embeds + embed_pos
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)

        # expand attention_mask
        if attention_mask is not None:
            # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
            attention_mask = _prepare_4d_attention_mask(attention_mask, inputs_embeds.dtype)

        encoder_states = () if output_hidden_states else None
        all_attentions = () if output_attentions else None

        # check if head_mask has a correct number of layers specified if desired
        if head_mask is not None:
            assert head_mask.shape[0] == (
                len(self.layers)
            ), f"The head_mask should be specified for {len(self.layers)} layers, but it is for {head_mask.shape[0]}."

        for idx, encoder_layer in enumerate(self.layers):
            if output_hidden_states:
                encoder_states = encoder_states + (hidden_states,)
            # add LayerDrop (see https://arxiv.org/abs/1909.11556 for description)
            to_drop = False
            if self.training:
                dropout_probability = ops.rand([])
                if dropout_probability < self.layerdrop:  # skip the layer
                    to_drop = True

            if to_drop:
                layer_outputs = (None, None)
            else:
                if self.gradient_checkpointing and self.training:
                    layer_outputs = self._gradient_checkpointing_func(
                        encoder_layer.__call__,
                        hidden_states,
                        attention_mask,
                        (head_mask[idx] if head_mask is not None else None),
                        output_attentions,
                    )
                else:
                    layer_outputs = encoder_layer(
                        hidden_states,
                        attention_mask,
                        layer_head_mask=(head_mask[idx] if head_mask is not None else None),
                        output_attentions=output_attentions,
                    )

                hidden_states = layer_outputs[0]

            if output_attentions:
                all_attentions = all_attentions + (layer_outputs[1],)

        hidden_states = self.layer_norm(hidden_states)
        if output_hidden_states:
            encoder_states = encoder_states + (hidden_states,)

        if not return_dict:
            return tuple(v for v in [hidden_states, encoder_states, all_attentions] if v is not None)
        return BaseModelOutput(
            last_hidden_state=hidden_states, hidden_states=encoder_states, attentions=all_attentions
        )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextEncoder.forward(input_features, attention_mask=None, head_mask=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
input_features

Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be obtained by loading a .flac or .wav audio file into an array of type List[float] or a numpy.ndarray, e.g. via the soundfile library (pip install soundfile). To prepare the array into input_features, the [AutoFeatureExtractor] should be used for extracting the fbank features, padding and conversion into a tensor of type mindspore.Tensor. See [~Speech2TextFeatureExtractor.__call__]

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length, feature_size)`

attention_mask

Mask to avoid performing convolution and attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

What are attention masks?

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

head_mask

Mask to nullify selected heads of the attention modules. Mask values selected in [0, 1]:

  • 1 indicates the head is not masked,
  • 0 indicates the head is masked.

TYPE: `mindspore.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional* DEFAULT: None

output_attentions

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: None

output_hidden_states

Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: None

return_dict

Whether or not to return a [~utils.ModelOutput] instead of a plain tuple.

TYPE: `bool`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
def forward(
    self,
    input_features,
    attention_mask=None,
    head_mask=None,
    output_attentions=None,
    output_hidden_states=None,
    return_dict=None,
):
    r"""
    Args:
        input_features (`mindspore.Tensor` of shape `(batch_size, sequence_length, feature_size)`):
            Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be
            obtained by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a
            `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into
            `input_features`, the [`AutoFeatureExtractor`] should be used for extracting the fbank features,
            padding and conversion into a tensor of type `mindspore.Tensor`. See
            [`~Speech2TextFeatureExtractor.__call__`]
        attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Mask to avoid performing convolution and attention on padding token indices. Mask values selected in
            `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.

            [What are attention masks?](../glossary#attention-mask)
        head_mask (`mindspore.Tensor` of shape `(encoder_layers, encoder_attention_heads)`, *optional*):
            Mask to nullify selected heads of the attention modules. Mask values selected in `[0, 1]`:

            - 1 indicates the head is **not masked**,
            - 0 indicates the head is **masked**.

        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
        output_hidden_states (`bool`, *optional*):
            Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
            for more detail.
        return_dict (`bool`, *optional*):
            Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
    """
    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict
    inputs_embeds = self.conv(input_features)
    inputs_embeds = self.embed_scale * inputs_embeds

    # subsample attention mask if necessary
    if attention_mask is not None:
        attention_mask = self._get_feature_vector_attention_mask(inputs_embeds.shape[1], attention_mask)
        padding_mask = attention_mask.ne(1).long()
    else:
        padding_mask = ops.zeros(inputs_embeds.shape[:2], dtype=mstype.long)

    embed_pos = self.embed_positions(padding_mask)

    hidden_states = inputs_embeds + embed_pos
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)

    # expand attention_mask
    if attention_mask is not None:
        # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
        attention_mask = _prepare_4d_attention_mask(attention_mask, inputs_embeds.dtype)

    encoder_states = () if output_hidden_states else None
    all_attentions = () if output_attentions else None

    # check if head_mask has a correct number of layers specified if desired
    if head_mask is not None:
        assert head_mask.shape[0] == (
            len(self.layers)
        ), f"The head_mask should be specified for {len(self.layers)} layers, but it is for {head_mask.shape[0]}."

    for idx, encoder_layer in enumerate(self.layers):
        if output_hidden_states:
            encoder_states = encoder_states + (hidden_states,)
        # add LayerDrop (see https://arxiv.org/abs/1909.11556 for description)
        to_drop = False
        if self.training:
            dropout_probability = ops.rand([])
            if dropout_probability < self.layerdrop:  # skip the layer
                to_drop = True

        if to_drop:
            layer_outputs = (None, None)
        else:
            if self.gradient_checkpointing and self.training:
                layer_outputs = self._gradient_checkpointing_func(
                    encoder_layer.__call__,
                    hidden_states,
                    attention_mask,
                    (head_mask[idx] if head_mask is not None else None),
                    output_attentions,
                )
            else:
                layer_outputs = encoder_layer(
                    hidden_states,
                    attention_mask,
                    layer_head_mask=(head_mask[idx] if head_mask is not None else None),
                    output_attentions=output_attentions,
                )

            hidden_states = layer_outputs[0]

        if output_attentions:
            all_attentions = all_attentions + (layer_outputs[1],)

    hidden_states = self.layer_norm(hidden_states)
    if output_hidden_states:
        encoder_states = encoder_states + (hidden_states,)

    if not return_dict:
        return tuple(v for v in [hidden_states, encoder_states, all_attentions] if v is not None)
    return BaseModelOutput(
        last_hidden_state=hidden_states, hidden_states=encoder_states, attentions=all_attentions
    )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextEncoderLayer

Bases: Module

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
class Speech2TextEncoderLayer(nn.Module):
    def __init__(self, config: Speech2TextConfig):
        super().__init__()
        self.embed_dim = config.d_model

        self.self_attn = SPEECH_TO_TEXT_ATTENTION_CLASSES[config._attn_implementation](
            embed_dim=self.embed_dim,
            num_heads=config.encoder_attention_heads,
            dropout=config.attention_dropout,
            config=config,
        )
        self.self_attn_layer_norm = nn.LayerNorm(self.embed_dim)
        self.dropout = config.dropout
        self.activation_fn = ACT2FN[config.activation_function]
        self.activation_dropout = config.activation_dropout
        self.fc1 = nn.Linear(self.embed_dim, config.encoder_ffn_dim)
        self.fc2 = nn.Linear(config.encoder_ffn_dim, self.embed_dim)
        self.final_layer_norm = nn.LayerNorm(self.embed_dim)

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        attention_mask: mindspore.Tensor,
        layer_head_mask: mindspore.Tensor,
        output_attentions: bool = False,
    ) -> mindspore.Tensor:
        """
        Args:
            hidden_states (`mindspore.Tensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`mindspore.Tensor`): attention mask of size
                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
            layer_head_mask (`mindspore.Tensor`): mask for attention heads in a given layer of size
                `(encoder_attention_heads,)`.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
        """
        residual = hidden_states
        hidden_states = self.self_attn_layer_norm(hidden_states)
        hidden_states, attn_weights, _ = self.self_attn(
            hidden_states=hidden_states,
            attention_mask=attention_mask,
            layer_head_mask=layer_head_mask,
            output_attentions=output_attentions,
        )
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
        hidden_states = residual + hidden_states

        residual = hidden_states
        hidden_states = self.final_layer_norm(hidden_states)
        hidden_states = self.activation_fn(self.fc1(hidden_states))
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.activation_dropout, training=self.training)
        hidden_states = self.fc2(hidden_states)
        hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
        hidden_states = residual + hidden_states

        if hidden_states.dtype == mstype.float16 and (
            ops.isinf(hidden_states).any() or ops.isnan(hidden_states).any()
        ):
            # clamp_value = torch.finfo(hidden_states.dtype).max - 1000
            clamp_value = Tensor(np.finfo(hidden_states.dtype).max) - 1000
            hidden_states = ops.clamp(hidden_states, min=-clamp_value, max=clamp_value)

        outputs = (hidden_states,)

        if output_attentions:
            outputs += (attn_weights,)

        return outputs

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextEncoderLayer.forward(hidden_states, attention_mask, layer_head_mask, output_attentions=False)

PARAMETER DESCRIPTION
hidden_states

input to the layer of shape (batch, seq_len, embed_dim)

TYPE: `mindspore.Tensor`

attention_mask

attention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.

TYPE: `mindspore.Tensor`

layer_head_mask

mask for attention heads in a given layer of size (encoder_attention_heads,).

TYPE: `mindspore.Tensor`

output_attentions

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: False

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
def forward(
    self,
    hidden_states: mindspore.Tensor,
    attention_mask: mindspore.Tensor,
    layer_head_mask: mindspore.Tensor,
    output_attentions: bool = False,
) -> mindspore.Tensor:
    """
    Args:
        hidden_states (`mindspore.Tensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
        attention_mask (`mindspore.Tensor`): attention mask of size
            `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
        layer_head_mask (`mindspore.Tensor`): mask for attention heads in a given layer of size
            `(encoder_attention_heads,)`.
        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
    """
    residual = hidden_states
    hidden_states = self.self_attn_layer_norm(hidden_states)
    hidden_states, attn_weights, _ = self.self_attn(
        hidden_states=hidden_states,
        attention_mask=attention_mask,
        layer_head_mask=layer_head_mask,
        output_attentions=output_attentions,
    )
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
    hidden_states = residual + hidden_states

    residual = hidden_states
    hidden_states = self.final_layer_norm(hidden_states)
    hidden_states = self.activation_fn(self.fc1(hidden_states))
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.activation_dropout, training=self.training)
    hidden_states = self.fc2(hidden_states)
    hidden_states = mindspore.ops.dropout(hidden_states, p=self.dropout, training=self.training)
    hidden_states = residual + hidden_states

    if hidden_states.dtype == mstype.float16 and (
        ops.isinf(hidden_states).any() or ops.isnan(hidden_states).any()
    ):
        # clamp_value = torch.finfo(hidden_states.dtype).max - 1000
        clamp_value = Tensor(np.finfo(hidden_states.dtype).max) - 1000
        hidden_states = ops.clamp(hidden_states, min=-clamp_value, max=clamp_value)

    outputs = (hidden_states,)

    if output_attentions:
        outputs += (attn_weights,)

    return outputs

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextForConditionalGeneration

Bases: Speech2TextPreTrainedModel

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
class Speech2TextForConditionalGeneration(Speech2TextPreTrainedModel):
    base_model_prefix = "model"
    _tied_weights_keys = ["lm_head.weight"]

    def __init__(self, config: Speech2TextConfig):
        super().__init__(config)
        self.model = Speech2TextModel(config)
        self.lm_head = nn.Linear(config.d_model, self.config.vocab_size, bias=False)

        # Initialize weights and apply final processing
        self.post_init()

    def get_encoder(self):
        return self.model.get_encoder()

    def get_decoder(self):
        return self.model.get_decoder()

    def get_output_embeddings(self):
        return self.lm_head

    def set_output_embeddings(self, new_embeddings):
        self.lm_head = new_embeddings

    def forward(
        self,
        input_features: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        decoder_input_ids: Optional[mindspore.Tensor] = None,
        decoder_attention_mask: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        decoder_head_mask: Optional[mindspore.Tensor] = None,
        cross_attn_head_mask: Optional[mindspore.Tensor] = None,
        encoder_outputs: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
        past_key_values: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
        decoder_inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]:
        r"""
        Args:
            labels (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the language modeling loss. Indices should either be in `[0, ..., config.vocab_size]`
                or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is
                only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Returns:
            Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]

        Example:
            ```python
            >>> import torch
            >>> from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
            >>> from datasets import load_dataset
            ...
            >>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
            >>> processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
            ...
            ...
            >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
            ...
            >>> inputs = processor(
            ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
            ... )
            >>> input_features = inputs.input_features
            ...
            >>> generated_ids = model.generate(inputs=input_features)
            ...
            >>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
            >>> transcription
            'mister quilter is the apostle of the middle classes and we are glad to welcome his gospel'
            ```
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if labels is not None:
            if decoder_input_ids is None and decoder_inputs_embeds is None:
                decoder_input_ids = shift_tokens_right(
                    labels, self.config.pad_token_id, self.config.decoder_start_token_id
                )

        outputs = self.model(
            input_features,
            attention_mask=attention_mask,
            decoder_input_ids=decoder_input_ids,
            encoder_outputs=encoder_outputs,
            decoder_attention_mask=decoder_attention_mask,
            head_mask=head_mask,
            decoder_head_mask=decoder_head_mask,
            cross_attn_head_mask=cross_attn_head_mask,
            past_key_values=past_key_values,
            decoder_inputs_embeds=decoder_inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        lm_logits = self.lm_head(outputs[0])

        loss = None
        if labels is not None:
            loss = ops.cross_entropy(lm_logits.view(-1, self.config.vocab_size), labels.view(-1))

        if not return_dict:
            output = (lm_logits,) + outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return Seq2SeqLMOutput(
            loss=loss,
            logits=lm_logits,
            past_key_values=outputs.past_key_values,
            decoder_hidden_states=outputs.decoder_hidden_states,
            decoder_attentions=outputs.decoder_attentions,
            cross_attentions=outputs.cross_attentions,
            encoder_last_hidden_state=outputs.encoder_last_hidden_state,
            encoder_hidden_states=outputs.encoder_hidden_states,
            encoder_attentions=outputs.encoder_attentions,
        )

    def prepare_inputs_for_generation(
        self,
        decoder_input_ids,
        past_key_values=None,
        attention_mask=None,
        head_mask=None,
        decoder_head_mask=None,
        cross_attn_head_mask=None,
        use_cache=None,
        encoder_outputs=None,
        **kwargs,
    ):
        # cut decoder_input_ids if past is used
        if past_key_values is not None:
            decoder_input_ids = decoder_input_ids[:, -1:]

        return {
            "encoder_outputs": encoder_outputs,
            "past_key_values": past_key_values,
            "decoder_input_ids": decoder_input_ids,
            "attention_mask": attention_mask,
            "head_mask": head_mask,
            "decoder_head_mask": decoder_head_mask,
            "cross_attn_head_mask": cross_attn_head_mask,
            "use_cache": use_cache,  # change this to avoid caching (presumably for debugging)
        }

    @staticmethod
    def _reorder_cache(past_key_values, beam_idx):
        reordered_past = ()
        for layer_past in past_key_values:
            reordered_past += (
                tuple(past_state.index_select(0, beam_idx) for past_state in layer_past),
            )
        return reordered_past

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextForConditionalGeneration.forward(input_features=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs=None, past_key_values=None, decoder_inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
labels

Labels for computing the language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

RETURNS DESCRIPTION
Union[Tuple[Tensor], Seq2SeqLMOutput]

Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]
Example 
>>> import torch
>>> from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
>>> from datasets import load_dataset
...
>>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
>>> processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
...
...
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
...
>>> inputs = processor(
...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
... )
>>> input_features = inputs.input_features
...
>>> generated_ids = model.generate(inputs=input_features)
...
>>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
>>> transcription
'mister quilter is the apostle of the middle classes and we are glad to welcome his gospel'
Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
def forward(
    self,
    input_features: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    decoder_input_ids: Optional[mindspore.Tensor] = None,
    decoder_attention_mask: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    decoder_head_mask: Optional[mindspore.Tensor] = None,
    cross_attn_head_mask: Optional[mindspore.Tensor] = None,
    encoder_outputs: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
    past_key_values: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
    decoder_inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]:
    r"""
    Args:
        labels (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the language modeling loss. Indices should either be in `[0, ..., config.vocab_size]`
            or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is
            only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

    Returns:
        Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]

    Example:
        ```python
        >>> import torch
        >>> from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
        >>> from datasets import load_dataset
        ...
        >>> model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
        >>> processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
        ...
        ...
        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        ...
        >>> inputs = processor(
        ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
        ... )
        >>> input_features = inputs.input_features
        ...
        >>> generated_ids = model.generate(inputs=input_features)
        ...
        >>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
        >>> transcription
        'mister quilter is the apostle of the middle classes and we are glad to welcome his gospel'
        ```
    """
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    if labels is not None:
        if decoder_input_ids is None and decoder_inputs_embeds is None:
            decoder_input_ids = shift_tokens_right(
                labels, self.config.pad_token_id, self.config.decoder_start_token_id
            )

    outputs = self.model(
        input_features,
        attention_mask=attention_mask,
        decoder_input_ids=decoder_input_ids,
        encoder_outputs=encoder_outputs,
        decoder_attention_mask=decoder_attention_mask,
        head_mask=head_mask,
        decoder_head_mask=decoder_head_mask,
        cross_attn_head_mask=cross_attn_head_mask,
        past_key_values=past_key_values,
        decoder_inputs_embeds=decoder_inputs_embeds,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )
    lm_logits = self.lm_head(outputs[0])

    loss = None
    if labels is not None:
        loss = ops.cross_entropy(lm_logits.view(-1, self.config.vocab_size), labels.view(-1))

    if not return_dict:
        output = (lm_logits,) + outputs[1:]
        return ((loss,) + output) if loss is not None else output

    return Seq2SeqLMOutput(
        loss=loss,
        logits=lm_logits,
        past_key_values=outputs.past_key_values,
        decoder_hidden_states=outputs.decoder_hidden_states,
        decoder_attentions=outputs.decoder_attentions,
        cross_attentions=outputs.cross_attentions,
        encoder_last_hidden_state=outputs.encoder_last_hidden_state,
        encoder_hidden_states=outputs.encoder_hidden_states,
        encoder_attentions=outputs.encoder_attentions,
    )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextModel

Bases: Speech2TextPreTrainedModel

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
class Speech2TextModel(Speech2TextPreTrainedModel):
    def __init__(self, config: Speech2TextConfig):
        super().__init__(config)

        self.encoder = Speech2TextEncoder(config)
        self.decoder = Speech2TextDecoder(config)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.decoder.embed_tokens

    def set_input_embeddings(self, value):
        self.decoder.embed_tokens = value

    def get_encoder(self):
        return self.encoder

    def get_decoder(self):
        return self.decoder


    def forward(
        self,
        input_features: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        decoder_input_ids: Optional[mindspore.Tensor] = None,
        decoder_attention_mask: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        decoder_head_mask: Optional[mindspore.Tensor] = None,
        cross_attn_head_mask: Optional[mindspore.Tensor] = None,
        encoder_outputs: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
        past_key_values: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
        decoder_inputs_embeds: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]:
        r"""

        Returns:
            Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]

        Example:
            ```python
            >>> import torch
            >>> from transformers import Speech2TextModel, AutoFeatureExtractor
            >>> from datasets import load_dataset
            ...
            >>> model = Speech2TextModel.from_pretrained("facebook/s2t-small-librispeech-asr")
            >>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/s2t-small-librispeech-asr")
            >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
            >>> inputs = feature_extractor(
            ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
            ... )
            >>> input_features = inputs.input_features
            >>> decoder_input_ids = mindspore.Tensor([[1, 1]]) * model.config.decoder_start_token_id
            >>> last_hidden_state = model(input_features, decoder_input_ids=decoder_input_ids).last_hidden_state
            >>> list(last_hidden_state.shape)
            [1, 2, 256]
            ```
         """

        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if encoder_outputs is None:
            encoder_outputs = self.encoder(
                input_features,
                attention_mask=attention_mask,
                head_mask=head_mask,
                output_attentions=output_attentions,
                output_hidden_states=output_hidden_states,
                return_dict=return_dict,
            )
        # If the user passed a tuple for encoder_outputs, we wrap it in a BaseModelOutput when return_dict=True
        elif return_dict and not isinstance(encoder_outputs, BaseModelOutput):
            encoder_outputs = BaseModelOutput(
                last_hidden_state=encoder_outputs[0],
                hidden_states=encoder_outputs[1] if len(encoder_outputs) > 1 else None,
                attentions=encoder_outputs[2] if len(encoder_outputs) > 2 else None,
            )

        # downsample encoder attention mask
        if attention_mask is not None:
            encoder_attention_mask = self._get_feature_vector_attention_mask(
                encoder_outputs[0].shape[1], attention_mask
            )
        else:
            encoder_attention_mask = None

        # decoder outputs consists of (dec_features, past_key_value, dec_hidden, dec_attn)
        decoder_outputs = self.decoder(
            input_ids=decoder_input_ids,
            attention_mask=decoder_attention_mask,
            encoder_hidden_states=encoder_outputs[0],
            encoder_attention_mask=encoder_attention_mask,
            head_mask=decoder_head_mask,
            cross_attn_head_mask=cross_attn_head_mask,
            past_key_values=past_key_values,
            inputs_embeds=decoder_inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        if not return_dict:
            return decoder_outputs + encoder_outputs

        return Seq2SeqModelOutput(
            last_hidden_state=decoder_outputs.last_hidden_state,
            past_key_values=decoder_outputs.past_key_values,
            decoder_hidden_states=decoder_outputs.hidden_states,
            decoder_attentions=decoder_outputs.attentions,
            cross_attentions=decoder_outputs.cross_attentions,
            encoder_last_hidden_state=encoder_outputs.last_hidden_state,
            encoder_hidden_states=encoder_outputs.hidden_states,
            encoder_attentions=encoder_outputs.attentions,
        )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextModel.forward(input_features=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, head_mask=None, decoder_head_mask=None, cross_attn_head_mask=None, encoder_outputs=None, past_key_values=None, decoder_inputs_embeds=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

RETURNS DESCRIPTION
Union[Tuple[Tensor], Seq2SeqLMOutput]

Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]
Example 
>>> import torch
>>> from transformers import Speech2TextModel, AutoFeatureExtractor
>>> from datasets import load_dataset
...
>>> model = Speech2TextModel.from_pretrained("facebook/s2t-small-librispeech-asr")
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/s2t-small-librispeech-asr")
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> inputs = feature_extractor(
...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
... )
>>> input_features = inputs.input_features
>>> decoder_input_ids = mindspore.Tensor([[1, 1]]) * model.config.decoder_start_token_id
>>> last_hidden_state = model(input_features, decoder_input_ids=decoder_input_ids).last_hidden_state
>>> list(last_hidden_state.shape)
[1, 2, 256]
Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
def forward(
    self,
    input_features: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    decoder_input_ids: Optional[mindspore.Tensor] = None,
    decoder_attention_mask: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    decoder_head_mask: Optional[mindspore.Tensor] = None,
    cross_attn_head_mask: Optional[mindspore.Tensor] = None,
    encoder_outputs: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
    past_key_values: Optional[Tuple[Tuple[mindspore.Tensor]]] = None,
    decoder_inputs_embeds: Optional[mindspore.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]:
    r"""

    Returns:
        Union[Tuple[mindspore.Tensor], Seq2SeqLMOutput]

    Example:
        ```python
        >>> import torch
        >>> from transformers import Speech2TextModel, AutoFeatureExtractor
        >>> from datasets import load_dataset
        ...
        >>> model = Speech2TextModel.from_pretrained("facebook/s2t-small-librispeech-asr")
        >>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/s2t-small-librispeech-asr")
        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        >>> inputs = feature_extractor(
        ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
        ... )
        >>> input_features = inputs.input_features
        >>> decoder_input_ids = mindspore.Tensor([[1, 1]]) * model.config.decoder_start_token_id
        >>> last_hidden_state = model(input_features, decoder_input_ids=decoder_input_ids).last_hidden_state
        >>> list(last_hidden_state.shape)
        [1, 2, 256]
        ```
     """

    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    use_cache = use_cache if use_cache is not None else self.config.use_cache
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    if encoder_outputs is None:
        encoder_outputs = self.encoder(
            input_features,
            attention_mask=attention_mask,
            head_mask=head_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
    # If the user passed a tuple for encoder_outputs, we wrap it in a BaseModelOutput when return_dict=True
    elif return_dict and not isinstance(encoder_outputs, BaseModelOutput):
        encoder_outputs = BaseModelOutput(
            last_hidden_state=encoder_outputs[0],
            hidden_states=encoder_outputs[1] if len(encoder_outputs) > 1 else None,
            attentions=encoder_outputs[2] if len(encoder_outputs) > 2 else None,
        )

    # downsample encoder attention mask
    if attention_mask is not None:
        encoder_attention_mask = self._get_feature_vector_attention_mask(
            encoder_outputs[0].shape[1], attention_mask
        )
    else:
        encoder_attention_mask = None

    # decoder outputs consists of (dec_features, past_key_value, dec_hidden, dec_attn)
    decoder_outputs = self.decoder(
        input_ids=decoder_input_ids,
        attention_mask=decoder_attention_mask,
        encoder_hidden_states=encoder_outputs[0],
        encoder_attention_mask=encoder_attention_mask,
        head_mask=decoder_head_mask,
        cross_attn_head_mask=cross_attn_head_mask,
        past_key_values=past_key_values,
        inputs_embeds=decoder_inputs_embeds,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    if not return_dict:
        return decoder_outputs + encoder_outputs

    return Seq2SeqModelOutput(
        last_hidden_state=decoder_outputs.last_hidden_state,
        past_key_values=decoder_outputs.past_key_values,
        decoder_hidden_states=decoder_outputs.hidden_states,
        decoder_attentions=decoder_outputs.attentions,
        cross_attentions=decoder_outputs.cross_attentions,
        encoder_last_hidden_state=encoder_outputs.last_hidden_state,
        encoder_hidden_states=encoder_outputs.hidden_states,
        encoder_attentions=encoder_outputs.attentions,
    )

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextPreTrainedModel

Bases: PreTrainedModel

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
class Speech2TextPreTrainedModel(PreTrainedModel):
    config_class = Speech2TextConfig
    base_model_prefix = "model"
    main_input_name = "input_features"
    supports_gradient_checkpointing = True

    def _init_weights(self, cell):
        std = self.config.init_std
        if isinstance(cell, (nn.Linear, nn.Conv1d)):
            cell.weight.set_data(initializer(Normal(std),
                                             cell.weight.shape, cell.weight.dtype))
            if cell.bias:
                cell.bias.set_data(initializer('zeros', cell.bias.shape, cell.bias.dtype))
        elif isinstance(cell, nn.Embedding):
            weight = np.random.normal(0.0, std, cell.weight.shape)
            if cell.padding_idx:
                weight[cell.padding_idx] = 0

    def _get_feat_extract_output_lengths(self, input_lengths: mindspore.Tensor):
        """
        Computes the output length of the convolutional layers
        """
        for i in range(self.config.num_conv_layers):
            input_lengths = (input_lengths - 1) // 2 + 1

        return input_lengths

    def _get_feature_vector_attention_mask(self, feature_vector_length, attention_mask):
        # generate creates 3D attention mask, because of the shape of input_features
        # convert it to 2D if thats the case
        if len(attention_mask.shape) > 2:
            attention_mask = attention_mask[:, :, -1]

        subsampled_lengths = self._get_feat_extract_output_lengths(attention_mask.sum(-1)).to(mstype.int64)
        bsz = attention_mask.shape[0]
        attention_mask = ops.zeros(
            (bsz, feature_vector_length), dtype=attention_mask.dtype
        )

        # these two operations makes sure that all values
        # before the output lengths indices are attended to
        attention_mask[(ops.arange(bsz), subsampled_lengths - 1)] = 1
        attention_mask = attention_mask.flip([-1]).cumsum(-1).flip([-1]).long()
        return attention_mask

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextSinusoidalPositionalEmbedding

Bases: Module

This module produces sinusoidal positional embeddings of any length.

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
class Speech2TextSinusoidalPositionalEmbedding(nn.Module):
    """This module produces sinusoidal positional embeddings of any length."""

    def __init__(self, num_positions: int, embedding_dim: int, padding_idx: Optional[int] = None):
        super().__init__()
        self.offset = 2
        self.embedding_dim = embedding_dim
        self.padding_idx = padding_idx
        self.weights = None
        self.make_weights(num_positions + self.offset, embedding_dim, padding_idx)

    def make_weights(self, num_embeddings: int, embedding_dim: int, padding_idx: Optional[int] = None):
        emb_weights = self.get_embedding(num_embeddings, embedding_dim, padding_idx)
        if self.weights is not None:
            # in forward put the weights on the correct dtype and device of the param
            emb_weights = emb_weights.to(dtype=self.weights.dtype)

        self.weights = mindspore.Parameter(emb_weights)
        self.weights.requires_grad = False
        # self.weights.detach_()

    @staticmethod
    def get_embedding(num_embeddings: int, embedding_dim: int, padding_idx: Optional[int] = None):
        """
        Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the
        description in Section 3.5 of "Attention Is All You Need".
        """
        half_dim = embedding_dim // 2
        emb = math.log(10000) / (half_dim - 1)
        emb = ops.exp(ops.arange(half_dim, dtype=mstype.int64).float() * -emb)
        emb = ops.arange(num_embeddings, dtype=mstype.int64).float().unsqueeze(1) * emb.unsqueeze(0)
        emb = ops.cat([ops.sin(emb), ops.cos(emb)], axis=1).view(num_embeddings, -1)
        if embedding_dim % 2 == 1:
            # zero pad
            emb = ops.cat([emb, ops.zeros(num_embeddings, 1)], axis=1)
        if padding_idx is not None:
            emb[padding_idx, :] = 0
        return emb.float()


    def forward(self, input_ids: mindspore.Tensor, past_key_values_length: int = 0):
        bsz, seq_len = input_ids.shape
        # Create the position ids from the input token ids. Any padded tokens remain padded.
        position_ids = self.create_position_ids_from_input_ids(input_ids, self.padding_idx, past_key_values_length)

        # expand embeddings if needed
        max_pos = self.padding_idx + 1 + seq_len
        if max_pos > self.weights.shape[0]:
            self.make_weights(max_pos + self.offset, self.embedding_dim, self.padding_idx)

        return self.weights.index_select(0, position_ids.view(-1)).view(bsz, seq_len, -1)#.detach()

    def create_position_ids_from_input_ids(
        self, input_ids: mindspore.Tensor, padding_idx: int, past_key_values_length: Optional[int] = 0
    ):
        """
        Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding
        symbols are ignored. This is modified from fairseq's `utils.make_positions`.

        Args:
            x (mindspore.Tensor): x.

        Returns:
            mindspore.Tensor
        """
        # The series of casts and type-conversions here are carefully balanced to both work with ONNX export and XLA.
        mask = input_ids.ne(padding_idx).int()
        incremental_indices = (ops.cumsum(mask, axis=1).type_as(mask) + past_key_values_length) * mask
        return incremental_indices.long() + padding_idx

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextSinusoidalPositionalEmbedding.create_position_ids_from_input_ids(input_ids, padding_idx, past_key_values_length=0)

Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols are ignored. This is modified from fairseq's utils.make_positions.

PARAMETER DESCRIPTION
x

x.

TYPE: Tensor

RETURNS DESCRIPTION

mindspore.Tensor
Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
def create_position_ids_from_input_ids(
    self, input_ids: mindspore.Tensor, padding_idx: int, past_key_values_length: Optional[int] = 0
):
    """
    Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding
    symbols are ignored. This is modified from fairseq's `utils.make_positions`.

    Args:
        x (mindspore.Tensor): x.

    Returns:
        mindspore.Tensor
    """
    # The series of casts and type-conversions here are carefully balanced to both work with ONNX export and XLA.
    mask = input_ids.ne(padding_idx).int()
    incremental_indices = (ops.cumsum(mask, axis=1).type_as(mask) + past_key_values_length) * mask
    return incremental_indices.long() + padding_idx

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.Speech2TextSinusoidalPositionalEmbedding.get_embedding(num_embeddings, embedding_dim, padding_idx=None) staticmethod

Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the description in Section 3.5 of "Attention Is All You Need".

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
@staticmethod
def get_embedding(num_embeddings: int, embedding_dim: int, padding_idx: Optional[int] = None):
    """
    Build sinusoidal embeddings. This matches the implementation in tensor2tensor, but differs slightly from the
    description in Section 3.5 of "Attention Is All You Need".
    """
    half_dim = embedding_dim // 2
    emb = math.log(10000) / (half_dim - 1)
    emb = ops.exp(ops.arange(half_dim, dtype=mstype.int64).float() * -emb)
    emb = ops.arange(num_embeddings, dtype=mstype.int64).float().unsqueeze(1) * emb.unsqueeze(0)
    emb = ops.cat([ops.sin(emb), ops.cos(emb)], axis=1).view(num_embeddings, -1)
    if embedding_dim % 2 == 1:
        # zero pad
        emb = ops.cat([emb, ops.zeros(num_embeddings, 1)], axis=1)
    if padding_idx is not None:
        emb[padding_idx, :] = 0
    return emb.float()

mindnlp.transformers.models.speech_to_text.modeling_speech_to_text.shift_tokens_right(input_ids, pad_token_id, decoder_start_token_id)

Shift input ids one token to the right.

Source code in mindnlp/transformers/models/speech_to_text/modeling_speech_to_text.py 
48
49
50
51
52
53
54
55
56
57
58
59
60
61
def shift_tokens_right(input_ids: mindspore.Tensor, pad_token_id: int, decoder_start_token_id: int):
    """
    Shift input ids one token to the right.
    """
    shifted_input_ids = input_ids.new_zeros(input_ids.shape)
    shifted_input_ids[:, 1:] = input_ids[:, :-1].clone()
    shifted_input_ids[:, 0] = decoder_start_token_id

    if pad_token_id is None:
        raise ValueError("self.model.config.pad_token_id has to be defined.")
    # replace possible -100 values in labels by `pad_token_id`
    shifted_input_ids.masked_fill_(shifted_input_ids == -100, pad_token_id)

    return shifted_input_ids