Patrick von Platen
961732c276
[Wav2Vec2] PyCTCDecode Integration to support language model boosted decoding ( #14339 )
...
* up
* up
* up
* make it cleaner
* correct
* make styhahalal
* add more tests
* finish
* small fix
* make style
* up
* tryout to solve cicrle ci
* up
* fix more tests
* fix more tests
* apply sylvains suggestions
* fix import
* correct docs
* add pyctcdecode only to speech tests
* fix more tests
* add tf, flax and pt tests
* add pt
* fix last tests
* fix more tests
* Apply suggestions from code review
* change lines
* Apply suggestions from code review
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
* correct tests
* correct tests
* add doc string
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
2021-12-08 12:07:54 +01:00
Nik
6645eb61fa
fix #14524 (IndexError when mask prob is too low) ( #14525 )
...
* fix #14524 (IndexError when mask prob is too low)
* fix formatting
* correct documentation, add option for setting min_num_masks
* change the semantic meaning of `mask_prob` in _compute_mask_indices
With this commit the meaing of `mask_prob` actually adhered to the probability for each
vector to be the start of a masked span of length.
* fix check_copies test
* fix documentation to semantic meaning of `upper bound of overall masking percentage`, revert changes to _compute_mask_indices
* fix typo
2021-12-02 17:05:31 +03:00
Patrick von Platen
700a748fe6
[Wav2Vec2] Add New Wav2Vec2 Translation ( #14392 )
...
* add new wav2vec2 translation
* correct
* up
* add tests
* correct end copy
* correct more
* up
* correct unispeech sat
* finish
* finalize
* finish
* up
2021-11-17 14:38:56 +01:00
Sylvain Gugger
040fd47162
Fix gradient_checkpointing backward compatibility ( #14408 )
...
* Fix gradient_checkpointing backward compatibility
* Remove needless line
* make sure mask prob is big enough and length small enough
* Fix tests
Co-authored-by: patrickvonplaten <patrick.v.platen@gmail.com>
2021-11-16 08:58:42 -05:00
Patrick von Platen
0c3174c758
Add TF<>PT and Flax<>PT everywhere ( #14047 )
...
* up
* up
* up
* up
* up
* up
* up
* add clip
* fix clip PyTorch
* fix clip PyTorch
* up
* up
* up
* up
* up
* up
* up
2021-10-25 23:55:08 +02:00
Patrick von Platen
bdf31d6e0a
[Speech] Move all examples to new audio feature ( #14045 )
...
* up
* up
* up
* finish
2021-10-18 12:52:40 +02:00
Patrick von Platen
7fb2a8b3d9
up ( #14008 )
2021-10-14 15:46:22 +02:00
Patrick von Platen
58bf882579
[Wav2Vec2] Make sure tensors are always bool for mask_indices ( #13977 )
...
* correct long to bool
* up
* correct code
2021-10-12 18:17:06 +02:00
Patrick von Platen
d45fc7da3d
[Speech Examples] Add pytorch speech pretraining ( #13877 )
...
* adapt wav2vec2
* add example
* add files
* adapt
* remove bogus file
* Apply suggestions from code review
* adapt files more
* upload changes
* del old files
* up
* up
* up
* up
* up
* correct gradient checkpoitning
* add readme
* finish
* finish
* up
* more fixes
* up
* up
* add demo run to readme
* up
2021-10-12 00:46:32 +02:00
Patrick von Platen
0f5488f79f
[Wav2Vec2] Fix mask_feature_prob ( #13921 )
...
* up
* overwrite hubert
2021-10-07 19:07:32 +03:00
Patrick von Platen
a75db353c4
[Slow tests] Disable Wav2Vec2 pretraining test for now ( #13303 )
...
* fix_torch_device_generate_test
* remove @
* wav2vec2 pretraining
Co-authored-by: Patrick von Platen <patrick@huggingface.co>
2021-08-30 06:03:02 -04:00
Anton Lozhkov
b6f332ecaf
Add Wav2Vec2 & Hubert ForSequenceClassification ( #13153 )
...
* Add hubert classifier + tests
* Add hubert classifier + tests
* Dummies for all classification tests
* Wav2Vec2 classifier + ER test
* Fix hubert integration tests
* Add hubert IC
* Pass tests for all classification tasks on Hubert
* Pass all tests + copies
* Move models to the SUPERB org
2021-08-27 20:52:51 +03:00
Patrick von Platen
f6e254474c
[Sequence Feature Extraction] Add truncation ( #12804 )
...
* fix_torch_device_generate_test
* remove @
* add truncate
* finish
* correct test
* Apply suggestions from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* clean tests
* correct normalization for truncation
* remove casting
* up
* save intermed
* finish
* finish
* correct
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2021-07-23 17:53:30 +02:00
Lysandre Debut
c3d9ac7607
Expose get_config() on ModelTesters ( #12812 )
...
* Expose get_config() on ModelTesters
* Typo
2021-07-21 04:13:11 -04:00
Patrick von Platen
b4b562d834
[Wav2Vec2] Padded vectors should not allowed to be sampled ( #12764 )
...
* fix_torch_device_generate_test
* remove @
* finish
* correct script
* correct script
2021-07-16 19:07:08 +02:00
Patrick von Platen
2e9fb13fb1
[Wav2Vec2] Correctly pad mask indices for PreTraining ( #12748 )
...
* fix_torch_device_generate_test
* remove @
* start adding tests
* correct wav2vec2 pretraining
* up
* up
Co-authored-by: Patrick von Platen <patrick@huggingface.co>
2021-07-15 21:40:25 +01:00
Patrick von Platen
27d348f2fe
[Wav2Vec2, Hubert] Fix ctc loss test ( #12458 )
...
* fix_torch_device_generate_test
* remove @
* fix test
2021-07-01 08:59:32 -04:00
Will Rice
bc084938f2
Add out of vocabulary error to ASR models ( #12288 )
...
* Add OOV error to ASR models
* Feedback changes
2021-06-29 08:57:46 +01:00
Patrick von Platen
bc6f51e539
[Wav2Vec2ForPretraining] Correct checkpoints wav2vec2 & fix tests ( #12089 )
...
* fix_torch_device_generate_test
* remove @
* fix tests
2021-06-09 20:41:59 +01:00
Anton Lozhkov
d472bd7b18
Wav2Vec2 Pretraining ( #11306 )
...
* Working quantizer forward
* Working quantizer forward
* Clean up unused model parts, test reproducibility
* Working quantizer forward
* Clean up unused model parts, test reproducibility
* Remove custom outputs from the shared ones
* correct conversion
* correct bug
* add first pretrain script
* save intermediate
* static shapes
* save intermediate
* finish first pretrain script version
* more refactor
* remove wanddb
* refactor more
* improve test
* correct perplexity compute bug
* finish model implementation
* add to docs
* finish docs
* finish pretraining script
* finish pretraining script
* remove wandb
* finish PR for merge
* finish config
* finish
* make deepspeed work
* Apply suggestions from code review
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* apply suggestions
* fix flaky test
Co-authored-by: patrickvonplaten <patrick.v.platen@gmail.com>
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2021-06-09 18:40:56 +01:00
Patrick von Platen
7630c11f32
[Wav2Vec2] SpecAugment Fast ( #11764 )
...
* first try
* finish
2021-05-25 13:59:52 +01:00
Patrick von Platen
3e3e41ae20
Pytorch - Lazy initialization of models ( #11471 )
...
* lazy_init_weights
* remove ipdb
* save int
* add necessary code
* remove unnecessary utils
* Update src/transformers/models/t5/modeling_t5.py
* clean
* add tests
* correct
* finish tests
* finish tests
* fix some more tests
* fix xlnet & transfo-xl
* fix more tests
* make sure tests are independent
* fix tests more
* finist tests
* final touches
* Update src/transformers/modeling_utils.py
* Apply suggestions from code review
* Update src/transformers/modeling_utils.py
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* Update src/transformers/modeling_utils.py
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* clean tests
* give arg positive name
* add more mock weights to xlnet
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
2021-05-05 17:22:20 +02:00
Sylvain Gugger
acc3bd9d2a
Enforce string-formatting with f-strings ( #10980 )
...
* First third
* Styling and fix mistake
* Quality
* All the rest
* Treat %s and %d
* typo
* Missing )
* Apply suggestions from code review
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
2021-03-31 10:00:27 -04:00
Patrick von Platen
0486ccdd3d
small improvements ( #10773 )
2021-03-17 18:10:17 +03:00
Patrick von Platen
d9e693e1d0
make wav2vec2 test deterministic ( #10714 )
2021-03-15 09:50:05 -04:00
Patrick von Platen
0234de8418
Add Fine-Tuning for Wav2Vec2 ( #10145 )
...
* add encode labels function to tokenizer
* start adding finetuning
* init dropout
* upload
* correct convert script
* apply changes
* fix second typo
* make first dummy training run
* adapt convert script
* push confg for comparison
* remove conf
* finish training
* adapt data collator
* add research folder
* update according to fairseq feedback
* some minor corrections
* refactor masking indices a bit
* some minor changes
* clean tokenizer
* finish clean-up
* remove previous logic
* update run script
* correct training
* finish changes
* finish model
* correct bug
* fix training a bit more
* add some tests
* finish gradient checkpointing
* finish example
* correct gradient checkpointing
* improve tokenization method
* revert changes in tokenizer
* revert general change
* adapt fine-tuning
* update
* save intermediate test
* Update README.md
* finish finetuning
* delete conversion script
* Update src/transformers/models/wav2vec2/configuration_wav2vec2.py
* Update src/transformers/models/wav2vec2/processing_wav2vec2.py
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
* finish wav2vec2 script
* finish wav2vec2 fine-tuning
* finalize test
* correct test
* adapt tests
* finish
* remove test file
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
2021-03-01 12:13:17 +03:00
Patrick von Platen
cb38ffcc5e
[PretrainedFeatureExtractor] + Wav2Vec2FeatureExtractor, Wav2Vec2Processor, Wav2Vec2Tokenizer ( #10324 )
...
* push to show
* small improvement
* small improvement
* Update src/transformers/feature_extraction_utils.py
* Update src/transformers/feature_extraction_utils.py
* implement base
* add common tests
* make all tests pass for wav2vec2
* make padding work & add more tests
* finalize feature extractor utils
* add call method to feature extraction
* finalize feature processor
* finish tokenizer
* finish general processor design
* finish tests
* typo
* remove bogus file
* finish docstring
* add docs
* finish docs
* small fix
* correct docs
* save intermediate
* load changes
* apply changes
* apply changes to doc
* change tests
* apply surajs recommend
* final changes
* Apply suggestions from code review
* fix typo
* fix import
* correct docstring
2021-02-25 17:42:46 +03:00
Patrick von Platen
495c157d6f
[Wav2Vec2] Improve Tokenizer & Model for batched inference ( #10117 )
...
* save intermediate
* finish batch the same as fairseq
* add normalization
* fix batched input
* add better comment
* Update src/transformers/models/wav2vec2/modeling_wav2vec2.py
* add nice docstring
* add tokenizer tests
* make all slow tests pass
* finish PR
* correct import
2021-02-11 15:40:54 +03:00
Patrick von Platen
b972125ced
Deprecate Wav2Vec2ForMaskedLM and add Wav2Vec2ForCTC ( #10089 )
...
* add wav2vec2CTC and deprecate for maskedlm
* remove from docs
2021-02-09 03:49:02 -05:00
Patrick von Platen
d6217fb30c
Wav2Vec2 ( #9659 )
...
* add raw scaffold
* implement feat extract layers
* make style
* remove +
* correctly convert weights
* make feat extractor work
* make feature extraction proj work
* run forward pass
* finish forward pass
* Succesful decoding example
* remove unused files
* more changes
* add wav2vec tokenizer
* add new structure
* fix run forward
* add other layer norm architecture
* finish 2nd structure
* add model tests
* finish tests for tok and model
* clean-up
* make style
* finish docstring for model and config
* make style
* correct docstring
* correct tests
* change checkpoints to fairseq
* fix examples
* finish wav2vec2
* make style
* apply sylvains suggestions
* apply lysandres suggestions
* change print to log.info
* re-add assert statement
* add input_values as required input name
* finish wav2vec2 tokenizer
* Update tests/test_tokenization_wav2vec2.py
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
* apply sylvains suggestions
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
2021-02-02 15:52:10 +03:00
