Skip to content

[Cherry-picked 0.10] Add pretrained weights from wav2vec2.0 and XLSR papers #1827

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 6, 2021
Merged

[Cherry-picked 0.10] Add pretrained weights from wav2vec2.0 and XLSR papers #1827

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
02b3150
Add pretrained weights from wav2vec2.0 and XLSR papers
mthrok Oct 5, 2021
23539b0
tweak
mthrok Oct 6, 2021
c240b0c
Update torchaudio/models/wav2vec2/pretrained.py
mthrok Oct 6, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions docs/source/models.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,45 @@ Pre-trained Models

.. autoproperty:: labels

.. 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:

.. autodata:: HUBERT_BASE
:no-value:

Expand Down
26 changes: 26 additions & 0 deletions test/integration_tests/wav2vec2_model_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,18 @@
import torchaudio
from torchaudio.models import (
WAV2VEC2_BASE,
WAV2VEC2_LARGE,
WAV2VEC2_LARGE_LV60K,
WAV2VEC2_ASR_BASE_10M,
WAV2VEC2_ASR_BASE_100H,
WAV2VEC2_ASR_BASE_960H,
WAV2VEC2_ASR_LARGE_10M,
WAV2VEC2_ASR_LARGE_100H,
WAV2VEC2_ASR_LARGE_960H,
WAV2VEC2_ASR_LARGE_LV60K_10M,
WAV2VEC2_ASR_LARGE_LV60K_100H,
WAV2VEC2_ASR_LARGE_LV60K_960H,
WAV2VEC2_XLSR53,
HUBERT_BASE,
HUBERT_LARGE,
HUBERT_XLARGE,
Expand All @@ -12,6 +25,10 @@
@pytest.mark.parametrize(
"bundle",
[
WAV2VEC2_BASE,
WAV2VEC2_LARGE,
WAV2VEC2_LARGE_LV60K,
WAV2VEC2_XLSR53,
HUBERT_BASE,
HUBERT_LARGE,
HUBERT_XLARGE,
Expand All @@ -25,6 +42,15 @@ def test_pretraining_models(bundle):
@pytest.mark.parametrize(
"bundle,expected",
[
(WAV2VEC2_ASR_BASE_10M, 'I|HAD|THAT|CURIYOSSITY|BESID|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_BASE_100H, 'I|HAD|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_BASE_960H, 'I|HAD|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_LARGE_10M, 'I|HAD|THAT|CURIOUSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_LARGE_100H, 'I|HAD|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_LARGE_960H, 'I|HAD|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_LARGE_LV60K_10M, 'I|HAD|THAT|CURIOUSSITY|BESID|ME|AT|THISS|MOMENT|'),
(WAV2VEC2_ASR_LARGE_LV60K_100H, 'I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(WAV2VEC2_ASR_LARGE_LV60K_960H, 'I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(HUBERT_ASR_LARGE, 'I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|'),
(HUBERT_ASR_XLARGE, 'I|HAVE|THAT|CURIOSITY|BESIDE|ME|AT|THIS|MOMENT|')
]
Expand Down
26 changes: 26 additions & 0 deletions torchaudio/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,19 @@
)
from .wav2vec2.pretrained import (
Wav2Vec2PretrainedModelBundle,
WAV2VEC2_BASE,
WAV2VEC2_LARGE,
WAV2VEC2_LARGE_LV60K,
WAV2VEC2_ASR_BASE_10M,
WAV2VEC2_ASR_BASE_100H,
WAV2VEC2_ASR_BASE_960H,
WAV2VEC2_ASR_LARGE_10M,
WAV2VEC2_ASR_LARGE_100H,
WAV2VEC2_ASR_LARGE_960H,
WAV2VEC2_ASR_LARGE_LV60K_10M,
WAV2VEC2_ASR_LARGE_LV60K_100H,
WAV2VEC2_ASR_LARGE_LV60K_960H,
WAV2VEC2_XLSR53,
HUBERT_BASE,
HUBERT_LARGE,
HUBERT_XLARGE,
Expand All @@ -45,6 +58,19 @@
'hubert_ft_large',
'hubert_ft_xlarge',
'Wav2Vec2PretrainedModelBundle',
'WAV2VEC2_BASE',
'WAV2VEC2_LARGE',
'WAV2VEC2_LARGE_LV60K',
'WAV2VEC2_ASR_BASE_10M',
'WAV2VEC2_ASR_BASE_100H',
'WAV2VEC2_ASR_BASE_960H',
'WAV2VEC2_ASR_LARGE_10M',
'WAV2VEC2_ASR_LARGE_100H',
'WAV2VEC2_ASR_LARGE_960H',
'WAV2VEC2_ASR_LARGE_LV60K_10M',
'WAV2VEC2_ASR_LARGE_LV60K_100H',
'WAV2VEC2_ASR_LARGE_LV60K_960H',
'WAV2VEC2_XLSR53',
'HUBERT_BASE',
'HUBERT_LARGE',
'HUBERT_XLARGE',
Expand Down
Loading