mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/librispeech/ASR/transducer
History
Fangjun Kuang 1d44da845b
RNN-T Conformer training for LibriSpeech (#143) 
* Begin to add RNN-T training for librispeech.

* Copy files from conformer_ctc.

Will edit it.

* Use conformer/transformer model as encoder.

* Begin to add training script.

* Add training code.

* Remove long utterances to avoid OOM when a large max_duraiton is used.

* Begin to add decoding script.

* Add decoding script.

* Minor fixes.

* Add beam search.

* Use LSTM layers for the encoder.

Need more tunings.

* Use stateless decoder.

* Minor fixes to make it ready for merge.

* Fix README.

* Update RESULT.md to include RNN-T Conformer.

* Minor fixes.

* Fix tests.

* Minor fixes.

* Minor fixes.

* Fix tests.
2021-12-18 07:42:51 +08:00
..
__init__.py
Apply layer normalization to the output of each gate in LSTM/GRU. (#139)
2021-12-07 18:38:03 +08:00
asr_datamodule.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
beam_search.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
conformer.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
decode.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
decoder.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
encoder_interface.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
export.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
joiner.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
model.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
pretrained.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
rnn.py
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_conformer.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_decoder.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_joiner.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_rnn.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_transducer.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_transformer.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
train.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
transformer.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00

README.md

Introduction

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

cd egs/librispeech/ASR

export CUDA_VISIBLE_DEVICES="0,1,2,3"

./transducer/train.py \
  --world-size 4 \
  --num-epochs 30 \
  --start-epoch 0 \
  --exp-dir transducer/exp \
  --full-libri 1 \
  --max-duration 250 \
  --lr-factor 2.5