models.rst 3.33 KB
Newer Older
Tomás Osório's avatar
Tomás Osório committed
1
2
3
4
.. role:: hidden
    :class: hidden-section

torchaudio.models
moto's avatar
moto committed
5
=================
Tomás Osório's avatar
Tomás Osório committed
6
7
8
9
10
11

.. currentmodule:: torchaudio.models

The models subpackage contains definitions of models for addressing common audio tasks.


moto's avatar
moto committed
12
13
ConvTasNet
~~~~~~~~~~
moto's avatar
moto committed
14
15
16
17
18
19

.. autoclass:: ConvTasNet

  .. automethod:: forward


moto's avatar
moto committed
20
21
DeepSpeech
~~~~~~~~~~
discort's avatar
discort committed
22
23
24
25
26
27

.. autoclass:: DeepSpeech

  .. automethod:: forward


28
29
30
Tacotron2
~~~~~~~~~

moto's avatar
moto committed
31
32
33
34
35
36
Model
-----

Tacotoron2
^^^^^^^^^^

37
38
39
40
41
42
43
44
45
46
.. autoclass:: Tacotron2

  .. automethod:: forward

  .. automethod:: infer

Factory Functions
-----------------

tacotron2
moto's avatar
moto committed
47
^^^^^^^^^
48
49
50
51

.. autofunction:: tacotron2


moto's avatar
moto committed
52
53
Wav2Letter
~~~~~~~~~~
Tomás Osório's avatar
Tomás Osório committed
54
55
56
57

.. autoclass:: Wav2Letter

  .. automethod:: forward
jimchen90's avatar
jimchen90 committed
58
59


moto's avatar
moto committed
60
61
Wav2Vec2.0 / HuBERT
~~~~~~~~~~~~~~~~~~~
moto's avatar
moto committed
62

moto's avatar
moto committed
63
64
65
Model
-----

moto's avatar
moto committed
66
Wav2Vec2Model
moto's avatar
moto committed
67
^^^^^^^^^^^^^
moto's avatar
moto committed
68
69
70
71
72
73
74
75
76
77

.. autoclass:: Wav2Vec2Model

  .. automethod:: extract_features

  .. automethod:: forward

Factory Functions
-----------------

78
79
80
81
82
83
wav2vec2_model
^^^^^^^^^^^^^^

.. autofunction:: wav2vec2_model


moto's avatar
moto committed
84
wav2vec2_base
moto's avatar
moto committed
85
^^^^^^^^^^^^^
moto's avatar
moto committed
86

moto's avatar
moto committed
87
88
.. autofunction:: wav2vec2_base

moto's avatar
moto committed
89
wav2vec2_large
moto's avatar
moto committed
90
^^^^^^^^^^^^^^
moto's avatar
moto committed
91

moto's avatar
moto committed
92
93
.. autofunction:: wav2vec2_large

moto's avatar
moto committed
94
wav2vec2_large_lv60k
moto's avatar
moto committed
95
^^^^^^^^^^^^^^^^^^^^
moto's avatar
moto committed
96

moto's avatar
moto committed
97
98
.. autofunction:: wav2vec2_large_lv60k

99
wav2vec2_ft_base
100
101
^^^^^^^^^^^^^^^^^

102
.. autofunction:: wav2vec2_ft_base
103

104
wav2vec2_ft_large
105
106
^^^^^^^^^^^^^^^^^^

107
.. autofunction:: wav2vec2_ft_large
108

109
wav2vec2_ft_large_lv60k
110
111
^^^^^^^^^^^^^^^^^^^^^^^^

112
.. autofunction:: wav2vec2_ft_large_lv60k
113

moto's avatar
moto committed
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
hubert_base
^^^^^^^^^^^

.. autofunction:: hubert_base

hubert_large
^^^^^^^^^^^^

.. autofunction:: hubert_large

hubert_xlarge
^^^^^^^^^^^^^

.. autofunction:: hubert_xlarge

129
hubert_ft_large
moto's avatar
moto committed
130
131
^^^^^^^^^^^^^^^^

132
.. autofunction:: hubert_ft_large
moto's avatar
moto committed
133

134
hubert_ft_xlarge
moto's avatar
moto committed
135
136
^^^^^^^^^^^^^^^^^

137
.. autofunction:: hubert_ft_xlarge
moto's avatar
moto committed
138

139
140
141
142
143
144
145
146
147
Pre-trained Models
------------------

.. autoclass:: Wav2Vec2PretrainedModelBundle

   .. automethod:: get_model

   .. autoproperty:: labels

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
   .. autodata:: WAV2VEC2_BASE
      :no-value:

   .. autodata:: WAV2VEC2_ASR_BASE_10M
      :no-value:

   .. autodata:: WAV2VEC2_ASR_BASE_100H
      :no-value:

   .. autodata:: WAV2VEC2_ASR_BASE_960H
      :no-value:

   .. autodata:: WAV2VEC2_LARGE
      :no-value:

   .. autodata:: WAV2VEC2_ASR_LARGE_10M
      :no-value:

   .. autodata:: WAV2VEC2_ASR_LARGE_100H
      :no-value:

   .. autodata:: WAV2VEC2_ASR_LARGE_960H
      :no-value:

   .. autodata:: WAV2VEC2_LARGE_LV60K
      :no-value:

   .. autodata:: WAV2VEC2_ASR_LARGE_LV60K_10M
      :no-value:

   .. autodata:: WAV2VEC2_ASR_LARGE_LV60K_100H
      :no-value:

   .. autodata:: WAV2VEC2_ASR_LARGE_LV60K_960H
      :no-value:

   .. autodata:: WAV2VEC2_XLSR53
      :no-value:

187
188
189
   .. autodata:: HUBERT_BASE
      :no-value:

190
191
192
193
194
195
   .. autodata:: HUBERT_LARGE
      :no-value:

   .. autodata:: HUBERT_XLARGE
      :no-value:

196
197
   .. autodata:: HUBERT_ASR_LARGE
      :no-value:
198

199
200
201
   .. autodata:: HUBERT_ASR_XLARGE
      :no-value:

202
203
204
Utility Functions
-----------------

205
206
.. currentmodule:: torchaudio.models.wav2vec2.utils

moto's avatar
moto committed
207
import_huggingface_model
moto's avatar
moto committed
208
^^^^^^^^^^^^^^^^^^^^^^^^
moto's avatar
moto committed
209

210
211
.. autofunction:: import_huggingface_model

moto's avatar
moto committed
212
import_fairseq_model
moto's avatar
moto committed
213
^^^^^^^^^^^^^^^^^^^^
moto's avatar
moto committed
214

moto's avatar
moto committed
215
216
.. autofunction:: import_fairseq_model

217
.. currentmodule:: torchaudio.models
moto's avatar
moto committed
218

moto's avatar
moto committed
219
220
WaveRNN
~~~~~~~
jimchen90's avatar
jimchen90 committed
221

moto's avatar
moto committed
222
223
224
225
226
227
Model
-----

WaveRNN
^^^^^^^

jimchen90's avatar
jimchen90 committed
228
229
230
.. autoclass:: WaveRNN

  .. automethod:: forward
moto's avatar
moto committed
231

232
233
  .. automethod:: infer

234
235
236
237
Factory Functions
-----------------

wavernn
moto's avatar
moto committed
238
^^^^^^^
239
240
241

.. autofunction:: wavernn

moto's avatar
moto committed
242
243
244
245
References
~~~~~~~~~~

.. footbibliography::