mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 01:52:41 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/librispeech/ASR/transducer_stateless_multi_datasets
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* Fix outdated decoding code.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
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
asr_datamodule.py
Don't use a lambda for dataloader's worker_init_fn. (#284)
2022-03-31 20:32:00 +08:00
beam_search.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
conformer.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
decode.py
Ignore padding frames during RNN-T decoding. (#358)
2022-05-13 07:39:14 +08:00
decoder.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
encoder_interface.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
export.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
gigaspeech.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
joiner.py
Fix joiner (#234)
2022-03-02 16:41:14 +08:00
librispeech.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
model.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
pretrained.py
Ignore padding frames during RNN-T decoding. (#358)
2022-05-13 07:39:14 +08:00
README.md
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
subsampling.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
test_asr_datamodule.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
test_decoder.py
Begin to use multiple datasets in training (#213)
2022-02-21 15:27:27 +08:00
train.py
Set the seed for dataloader. (#282)
2022-03-31 16:48:46 +08:00
transformer.py
Fix joiner (#234)
2022-03-02 16:41:14 +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/librispeech/ASR
./prepare.sh
./prepare_giga_speech.sh

export CUDA_VISIBLE_DEVICES="0,1"

./transducer_stateless_multi_datasets/train.py \
  --world-size 2 \
  --num-epochs 60 \
  --start-epoch 0 \
  --exp-dir transducer_stateless_multi_datasets/exp-100 \
  --full-libri 0 \
  --max-duration 300 \
  --lr-factor 1 \
  --bpe-model data/lang_bpe_500/bpe.model \
  --modified-transducer-prob 0.25
  --giga-prob 0.2