Introduction

This repo contains pre-trained model using https://github.com/k2-fsa/icefall/pull/248.

It is trained on full LibriSpeech dataset using pruned RNN-T loss from k2.

How to clone this repo

sudo apt-get install git-lfs
git clone https://huggingface.co./csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless-2022-03-12

cd icefall-asr-librispeech-pruned-transducer-stateless-2022-03-12
git lfs pull

Caution: You have to run git lfs pull. Otherwise, you will be SAD later.

The model in this repo is trained using the commit 1603744469d167d848e074f2ea98c587153205fa.

You can use

git clone https://github.com/k2-fsa/icefall
cd icefall
git checkout 1603744469d167d848e074f2ea98c587153205fa

to download icefall.

The decoder architecture is modified from Rnn-Transducer with Stateless Prediction Network. A Conv1d layer is placed right after the input embedding layer.

Description

This repo provides pre-trained transducer Conformer model for the LibriSpeech dataset using icefall. There are no RNNs in the decoder. The decoder is stateless and contains only an embedding layer and a Conv1d.

The commands for training are:

cd egs/librispeech/ASR/
./prepare.sh

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

. path.sh

./pruned_transducer_stateless/train.py \
  --world-size 8 \
  --num-epochs 60 \
  --start-epoch 0 \
  --exp-dir pruned_transducer_stateless/exp \
  --full-libri 1 \
  --max-duration 300 \
  --prune-range 5 \
  --lr-factor 5 \
  --lm-scale 0.25

The tensorboard training log can be found at https://tensorboard.dev/experiment/WKRFY5fYSzaVBHahenpNlA/

The command for decoding is:

epoch=42
avg=11
sym=1

# greedy search

./pruned_transducer_stateless/decode.py \
  --epoch $epoch \
  --avg $avg \
  --exp-dir ./pruned_transducer_stateless/exp \
  --max-duration 100 \
  --decoding-method greedy_search \
  --beam-size 4 \
  --max-sym-per-frame $sym

# modified beam search
./pruned_transducer_stateless/decode.py \
  --epoch $epoch \
  --avg $avg \
  --exp-dir ./pruned_transducer_stateless/exp \
  --max-duration 100 \
  --decoding-method modified_beam_search \
  --beam-size 4

# beam search
# (not recommended)
./pruned_transducer_stateless/decode.py \
  --epoch $epoch \
  --avg $avg \
  --exp-dir ./pruned_transducer_stateless/exp \
  --max-duration 100 \
  --decoding-method beam_search \
  --beam-size 4

You can find the decoding log for the above command in this repo (in the folder log).

The WERs for the test datasets are

	test-clean	test-other	comment
greedy search (max sym per frame 1)	2.62	6.37	--epoch 42, --avg 11, --max-duration 100
greedy search (max sym per frame 2)	2.62	6.37	--epoch 42, --avg 11, --max-duration 100
greedy search (max sym per frame 3)	2.62	6.37	--epoch 42, --avg 11, --max-duration 100
modified beam search (beam size 4)	2.56	6.27	--epoch 42, --avg 11, --max-duration 100
beam search (beam size 4)	2.57	6.27	--epoch 42, --avg 11, --max-duration 100

File description

log, this directory contains the decoding log and decoding results
test_wavs, this directory contains wave files for testing the pre-trained model
data, this directory contains files generated by prepare.sh
exp, this directory contains only one file: preprained.pt

exp/pretrained.pt is generated by the following command:

epoch=42
avg=11

./pruned_transducer_stateless/export.py \
  --exp-dir ./pruned_transducer_stateless/exp \
  --bpe-model data/lang_bpe_500/bpe.model \
  --epoch $epoch \
  --avg $avg

HINT: To use pretrained.pt to compute the WER for test-clean and test-other, just do the following:

cp icefall-asr-librispeech-pruned-transducer-stateless-2022-03-12/exp/pretrained.pt \
  /path/to/icefall/egs/librispeech/ASR/pruned_transducer_stateless/exp/epoch-999.pt

and pass --epoch 999 --avg 1 to pruned_transducer_stateless/decode.py.