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
Desh Raj d110b04ad3 apply new black formatting to all files
2022-11-16 13:06:43 -05:00
..
__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
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
conformer.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
decode.py
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
decoder.py
Fix some typos. (#329)
2022-04-22 15:54:59 +08:00
encoder_interface.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
export.py
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
joiner.py
Minor fixes to the RNN-T Conformer model (#152)
2021-12-23 13:54:25 +08:00
model.py
Fix torch.nn.Embedding error for torch below 1.8.0 (#198)
2022-02-06 21:59:54 +08:00
pretrained.py
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
README.md
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
rnn.py
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
subsampling.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_conformer.py
Minor fixes to the RNN-T Conformer model (#152)
2021-12-23 13:54:25 +08:00
test_decoder.py
Minor fixes to the RNN-T Conformer model (#152)
2021-12-23 13:54:25 +08:00
test_joiner.py
RNN-T Conformer training for LibriSpeech (#143)
2021-12-18 07:42:51 +08:00
test_rnn.py
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
test_transducer.py
Minor fixes to the RNN-T Conformer model (#152)
2021-12-23 13:54:25 +08:00
test_transformer.py
Minor fixes to the RNN-T Conformer model (#152)
2021-12-23 13:54:25 +08:00
train.py
apply new black formatting to all files
2022-11-16 13:06:43 -05:00
transformer.py
Fix joiner (#234)
2022-03-02 16:41:14 +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