icefall

mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 18:12:19 +00:00

History

* shuffled full/partial librispeech data

* fixed the code style issue

* Shuffled full librispeech data off-line

* Fixed style, addressed comments, and removed redandunt codes

* Used the suggested version of black

* Propagated the changes to other folders for librispeech (except
conformer_mmi and streaming_conformer_ctc)

2022-11-27 11:26:09 +08:00

__init__.py

Limit the number of symbols per frame in RNN-T decoding. (#151 )

2021-12-18 11:00:42 +08:00

asr_datamodule.py

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

beam_search.py

apply black on all files

2022-11-17 09:42:17 -05:00

decode.py

apply black on all files

2022-11-17 09:42:17 -05:00

decoder.py

Fix some typos. (#329 )

2022-04-22 15:54:59 +08:00

encoder_interface.py

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

encoder.py

apply black on all files

2022-11-17 09:42:17 -05:00

joiner.py

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

model.py

Various fixes to support torch script. (#371 )

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

noam.py

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

README.md

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

subsampling.py

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

test_encoder.py

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

train.py

shuffle full Librispeech data (#574 )

2022-11-27 11:26:09 +08:00

README.md

Introduction

The encoder consists of LSTM layers in this folder. You can use the following command to start the training:

cd egs/librispeech/ASR

export CUDA_VISIBLE_DEVICES="0,1,2"

./transducer_lstm/train.py \
  --world-size 3 \
  --num-epochs 30 \
  --start-epoch 0 \
  --exp-dir transducer_lstm/exp \
  --full-libri 1 \
  --max-duration 300 \
  --lr-factor 3