This repository has been archived on 2026-03-23. You can view files and clone it, but cannot push or open issues or pull requests.

Fangjun Kuang e334e570d8

Filter utterances with number_tokens > number_feature_frames. (#604)

2022-11-12 07:57:58 +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

Add modified_beam_search for streaming decode (#489)

2022-07-25 16:53:23 +08:00

conformer.py

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

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

decode_stream.py

Sort results to make it more convenient to compare decoding results (#522)

2022-08-12 07:12:50 +08:00

decode.py

Fix LG log file name (#657)

2022-11-03 23:12:35 +08:00

decoder.py

Tedlium3 pruned transducer stateless (#261)

2022-04-11 17:08:53 +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

Using streaming conformer as transducer encoder (#380)

2022-06-28 00:18:54 +08:00

joiner.py

Add streaming Emformer stateless RNN-T. (#390)

2022-06-01 14:31:47 +08:00

model.py

Use ScaledLSTM as streaming encoder (#479)

2022-08-19 14:38:45 +08:00

pretrained.py

Using streaming conformer as transducer encoder (#380)

2022-06-28 00:18:54 +08:00

streaming_beam_search.py

Add modified_beam_search for streaming decode (#489)

2022-07-25 16:53:23 +08:00

streaming_decode.py

Sort results to make it more convenient to compare decoding results (#522)

2022-08-12 07:12:50 +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

Various fixes to support torch script. (#371)

2022-05-16 21:46:59 +08:00

test_model.py

Apply delay penalty on transducer (#654)

2022-11-04 16:10:09 +08:00

train.py

Filter utterances with number_tokens > number_feature_frames. (#604)

2022-11-12 07:57:58 +08:00

transformer.py

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

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