mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 18:12:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/aishell/ASR/transducer_stateless
History
Fangjun Kuang aeb8986e35
Ignore padding frames during RNN-T decoding. (#358) 
* Ignore padding frames during RNN-T decoding.

* Fix outdated decoding code.

* Minor fixes.
2022-05-13 07:39:14 +08:00
..
__init__.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
asr_datamodule.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
beam_search.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
conformer.py
Ignore padding frames during RNN-T decoding. (#358)
2022-05-13 07:39:14 +08:00
decode.py
update aishell-1 recipe with k2.rnnt_loss (#215)
2022-02-19 15:56:39 +08:00
decoder.py
Minor fixes (#193)
2022-01-27 18:01:17 +08:00
encoder_interface.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
export.py
Do some changes for aishell/ASR/transducer stateless/export.py (#347)
2022-05-07 11:09:31 +08:00
joiner.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
model.py
Add modified transducer loss for AIShell dataset (#219)
2022-03-02 16:02:38 +08:00
pretrained.py
Minor fixes (#193)
2022-01-27 18:01:17 +08:00
README.md
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
subsampling.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
test_decoder.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00
train.py
Reset seed at the beginning of each epoch. (#221)
2022-02-21 15:16:39 +08:00
transformer.py
add transducer_stateless with char unit to AIShell (#164)
2022-01-01 18:32:08 +08:00

README.md

Introduction

The decoder, i.e., the prediction network, is from https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9054419 (Rnn-Transducer with Stateless Prediction Network)

You can use the following command to start the training:

cd egs/aishell/ASR

export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"

./transducer_stateless/train.py \
  --world-size 8 \
  --num-epochs 30 \
  --start-epoch 0 \
  --exp-dir transducer_stateless/exp \
  --max-duration 250 \
  --lr-factor 2.5