Fangjun Kuang 0f45356ee6

Add streaming feature extractor. (#302) ...

* Add streaming feature extractor.

* Parallel streaming decode with greedy search.

* Fix typos.

* Use torch.stack() to replace torch.cat()

2022-04-18 10:38:56 +08:00

..

__init__.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

asr_datamodule.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

beam_search.py

Use Emformer as RNN-T encoder. (#278)

2022-04-02 13:37:39 +08:00

conformer.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

decode.py

Support specifying iteration number of checkpoints for decoding. (#289)

2022-04-03 13:02:08 +08:00

decoder.py

Add fast beam search decoding (#250)

2022-03-21 16:22:25 +08:00

encoder_interface.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

export.py

Add modified beam search for pruned rnn-t. (#248)

2022-03-12 16:16:55 +08:00

joiner.py

Add streaming feature extractor. (#302)

2022-04-18 10:38:56 +08:00

model.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

pretrained.py

Batch decoding for models trained with optimized_transducer (#267)

2022-03-23 19:11:34 +08:00

subsampling.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

test_decoder.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00

train.py

Set the seed for dataloader. (#282)

2022-03-31 16:48:46 +08:00

transformer.py

Use k2 pruned transducer loss to train conformer-transducer model (#194)

2022-02-17 13:33:54 +08:00