icefall/egs/librispeech/ASR/RESULTS.md

Results

LibriSpeech BPE training results (Transducer)

2021-12-22

Conformer encoder + non-current decoder. The decoder contains only an embedding layer and a Conv1d (with kernel size 2).

The WERs are

	test-clean	test-other	comment
greedy search	2.99	7.52	--epoch 20, --avg 10, --max-duration 100
beam search (beam size 2)	2.95	7.43
beam search (beam size 3)	2.94	7.37
beam search (beam size 4)	2.92	7.37
beam search (beam size 5)	2.93	7.38
beam search (beam size 8)	2.92	7.38

The training command for reproducing is given below:

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

./transducer_stateless/train.py \
  --world-size 4 \
  --num-epochs 30 \
  --start-epoch 0 \
  --exp-dir transducer_stateless/exp-full \
  --full-libri 1 \
  --max-duration 250 \
  --lr-factor 3

The tensorboard training log can be found at https://tensorboard.dev/experiment/PsJ3LgkEQfOmzedAlYfVeg/#scalars&_smoothingWeight=0

The decoding command is:

epoch=20
avg=10

## greedy search
./transducer_stateless/decode.py \
  --epoch $epoch \
  --avg $avg \
  --exp-dir transducer_stateless/exp-full \
  --bpe-model ./data/lang_bpe_500/bpe.model \
  --max-duration 100

## beam search
./transducer_stateless/decode.py \
  --epoch $epoch \
  --avg $avg \
  --exp-dir transducer_stateless/exp-full \
  --bpe-model ./data/lang_bpe_500/bpe.model \
  --max-duration 100 \
  --decoding-method beam_search \
  --beam-size 4

2021-12-17

Using commit cb04c8a7509425ab45fae888b0ca71bbbd23f0de.

Conformer encoder + LSTM decoder.

The best WER is

	test-clean	test-other
WER	3.16	7.71

using --epoch 26 --avg 12 with greedy search.

The training command to reproduce the above WER is:

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

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

The decoding command is:

epoch=26
avg=12

./transducer/decode.py \
  --epoch $epoch \
  --avg $avg \
  --exp-dir transducer/exp-lr-2.5-full \
  --bpe-model ./data/lang_bpe_500/bpe.model \
  --max-duration 100

You can find the tensorboard log at: https://tensorboard.dev/experiment/PYIbeD6zRJez1ViXaRqqeg/

LibriSpeech BPE training results (Conformer-CTC)

2021-11-09

The best WER, as of 2021-11-09, for the librispeech test dataset is below (using HLG decoding + n-gram LM rescoring + attention decoder rescoring):

	test-clean	test-other
WER	2.42	5.73

Scale values used in n-gram LM rescoring and attention rescoring for the best WERs are:

ngram_lm_scale	attention_scale
2.0	2.0

To reproduce the above result, use the following commands for training:

cd egs/librispeech/ASR/conformer_ctc
./prepare.sh
export CUDA_VISIBLE_DEVICES="0,1,2,3"
./conformer_ctc/train.py \
  --exp-dir conformer_ctc/exp_500_att0.8 \
  --lang-dir data/lang_bpe_500 \
  --att-rate 0.8 \
  --full-libri 1 \
  --max-duration 200 \
  --concatenate-cuts 0 \
  --world-size 4 \
  --bucketing-sampler 1 \
  --start-epoch 0 \
  --num-epochs 90
# Note: It trains for 90 epochs, but the best WER is at epoch-77.pt

and the following command for decoding

./conformer_ctc/decode.py \
  --exp-dir conformer_ctc/exp_500_att0.8 \
  --lang-dir data/lang_bpe_500 \
  --max-duration 30 \
  --concatenate-cuts 0 \
  --bucketing-sampler 1 \
  --num-paths 1000 \
  --epoch 77 \
  --avg 55 \
  --method attention-decoder \
  --nbest-scale 0.5

You can find the pre-trained model by visiting https://huggingface.co/csukuangfj/icefall-asr-librispeech-conformer-ctc-jit-bpe-500-2021-11-09

The tensorboard log for training is available at https://tensorboard.dev/experiment/hZDWrZfaSqOMqtW0NEfXKg/#scalars

2021-08-19

(Wei Kang): Result of https://github.com/k2-fsa/icefall/pull/13

TensorBoard log is available at https://tensorboard.dev/experiment/GnRzq8WWQW62dK4bklXBTg/#scalars

Pretrained model is available at https://huggingface.co/pkufool/icefall_asr_librispeech_conformer_ctc

The best decoding results (WER) are listed below, we got this results by averaging models from epoch 15 to 34, and using attention-decoder decoder with num_paths equals to 100.

	test-clean	test-other
WER	2.57%	5.94%

To get more unique paths, we scaled the lattice.scores with 0.5 (see https://github.com/k2-fsa/icefall/pull/10#discussion_r690951662 for more details), we searched the lm_score_scale and attention_score_scale for best results, the scales that produced the WER above are also listed below.

	lm_scale	attention_scale
test-clean	1.3	1.2
test-other	1.2	1.1

You can use the following commands to reproduce our results:

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

# It was using ef233486, you may not need to switch to it
# git checkout ef233486

cd egs/librispeech/ASR
./prepare.sh

export CUDA_VISIBLE_DEVICES="0,1,2,3"
python conformer_ctc/train.py --bucketing-sampler True \
                              --concatenate-cuts False \
                              --max-duration 200 \
                              --full-libri True \
                              --world-size 4 \
                              --lang-dir data/lang_bpe_5000

python conformer_ctc/decode.py --nbest-scale 0.5 \
                               --epoch 34 \
                               --avg 20 \
                               --method attention-decoder \
                               --max-duration 20 \
                               --num-paths 100 \
                               --lang-dir data/lang_bpe_5000

LibriSpeech training results (Tdnn-Lstm)

2021-08-24

(Wei Kang): Result of phone based Tdnn-Lstm model.

Icefall version: caa0b9e942

Pretrained model is available at https://huggingface.co/pkufool/icefall_asr_librispeech_tdnn-lstm_ctc

The best decoding results (WER) are listed below, we got this results by averaging models from epoch 19 to 14, and using whole-lattice-rescoring decoding method.

	test-clean	test-other
WER	6.59%	17.69%

We searched the lm_score_scale for best results, the scales that produced the WER above are also listed below.

	lm_scale
test-clean	0.8
test-other	0.9