Fangjun Kuang b1c3705fbe Compute the Nbest oracle WER for RNN-T decoding.

2022-04-24 15:10:30 +08:00

..

asr_datamodule.py

Support specifying number of workers for on-the-fly feature extraction.

2022-04-14 10:26:45 +08:00

beam_search.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

conformer.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

decode-giga.py

Fix decoding the gigaspeech dataset.

2022-04-18 15:23:07 +08:00

decode.py

Compute the Nbest oracle WER for RNN-T decoding.

2022-04-24 15:10:30 +08:00

decoder.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

encoder_interface.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

gigaspeech_scoring.py

Add decoding code for GigaSpeech.

2022-04-18 13:27:53 +08:00

gigaspeech.py

Add decoding code for GigaSpeech.

2022-04-18 13:27:53 +08:00

joiner.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

librispeech.py

Use librispeech + gigaspeech with modified conformer.

2022-04-12 17:28:01 +08:00

model.py

Use librispeech + gigaspeech with modified conformer.

2022-04-12 17:28:01 +08:00

optim.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

scaling.py

Copy files for editing.

2022-04-12 16:16:40 +08:00

train.py

Combine XL splits lazily during training.

2022-04-17 21:45:55 +08:00