Commits · c4893ca6eaefda846088f27df1fd38471a9c8640 · OpenDAS / Fairseq

"docs/vscode:/vscode.git/clone" did not exist on "8125372bbdf2c35a6ac7361b6343d9a3d175ca1c"

10 Oct, 2019 1 commit

Add ctc loss to ASR task (#1233) · c4893ca6

Dmytro Okhonko authored Oct 10, 2019

Summary:
Adds CTC loss and corresponding transformer ctc based models.

Tested with
`CUDA_VISIBLE_DEVICES=0 python train.py $DATA_PATH --save-dir $SAVE_DIR --max-epoch 30 --task speech_recognition --arch vggtransformer_enc_1 --optimizer adadelta --lr 1.0 --adadelta-eps 1e-8 --adadelta-rho 0.95 --clip-norm 10.0  --max-tokens 10000 --log-format json --log-interval 1 --criterion ctc_loss --user-dir examples/speech_recognition/ --validate-interval=10`
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1233

Reviewed By: jcai1

Differential Revision: D17856824

Pulled By: okhonko

fbshipit-source-id: f3eac64d3fdd0c37cf8c539dd360cfb610d8a6ef

c4893ca6

08 Aug, 2019 1 commit

Asr initial push (#810) · 72f9364c

Dmytro Okhonko authored Aug 08, 2019

Summary:
Initial code for speech recognition task.
Right now only one ASR model added - https://arxiv.org/abs/1904.11660

unit test testing:
python -m unittest discover tests

also run model training with this code and obtained
5.0 test_clean | 13.4 test_other
on librispeech with pytorch/audio features
Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/810

Reviewed By: cpuhrsch

Differential Revision: D16706659

Pulled By: okhonko

fbshipit-source-id: 89a5f9883e50bc0e548234287aa0ea73f7402514

72f9364c