mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-08 08:34:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

add results

Browse Source
This commit is contained in:
Desh Raj 2022-05-12 22:07:21 -04:00
parent f62f8fba20
commit 72d38950d1
4 changed files with 53 additions and 302 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
egs/spgispeech/ASR/README.md
View File

@ -1,21 +1,34 @@
# SPGISpeech
# Introduction SPGISpeech consists of 5,000 hours of recorded company earnings calls and their respective
transcriptions. The original calls were split into slices ranging from 5 to 15 seconds in
length to allow easy training for speech recognition systems. Calls represent a broad
cross-section of international business English; SPGISpeech contains approximately 50,000
speakers, one of the largest numbers of any speech corpus, and offers a variety of L1 and
L2 English accents. The format of each WAV file is single channel, 16kHz, 16 bit audio.
Please refer to <https://icefall.readthedocs.io/en/latest/recipes/librispeech.html> Transcription text represents the output of several stages of manual post-processing.
for how to run models in this recipe. As such, the text contains polished English orthography following a detailed style guide,
including proper casing, punctuation, and denormalized non-standard words such as numbers
and acronyms, making SPGISpeech suited for training fully formatted end-to-end models.
# Transducers Official reference:
There are various folders containing the name `transducer` in this folder. O’Neill, P.K., Lavrukhin, V., Majumdar, S., Noroozi, V., Zhang, Y., Kuchaiev, O., Balam,
The following table lists the differences among them. J., Dovzhenko, Y., Freyberg, K., Shulman, M.D., Ginsburg, B., Watanabe, S., & Kucsko, G.
(2021). SPGISpeech: 5, 000 hours of transcribed financial audio for fully formatted
end-to-end speech recognition. ArXiv, abs/2104.02014.
| | Encoder | Decoder | Comment | ArXiv link: https://arxiv.org/abs/2104.02014
|---------------------------------------|-----------|--------------------|---------------------------------------------------|
| `transducer` | Conformer | LSTM | | ## Performance Record
| `transducer_stateless` | Conformer | Embedding + Conv1d | |
| `transducer_lstm` | LSTM | LSTM | | | Decoding method | val |
| `transducer_stateless_multi_datasets` | Conformer | Embedding + Conv1d | Using data from GigaSpeech as extra training data | |---------------------------|------------|
| greedy search | 2.40 |
| beam search | 2.24 |
| modified beam search | 2.30 |
| fast beam search | 2.35 |
See [RESULTS](/egs/spgispeech/ASR/RESULTS.md) for details.
The decoder in `transducer_stateless` is modified from the paper
[Rnn-Transducer with Stateless Prediction Network](https://ieeexplore.ieee.org/document/9054419/).
We place an additional Conv1d layer right after the input embedding layer.

292
egs/spgispeech/ASR/RESULTS.md
View File

@ -1,6 +1,8 @@
## Results ## Results
### LibriSpeech BPE training results (Pruned Transducer) ### SPGISpeech BPE training results (Pruned Transducer)
#### 2022-05-11
#### Conformer encoder + embedding decoder #### Conformer encoder + embedding decoder
@ -10,25 +12,32 @@ layer (to transform tensor dim).
The WERs are The WERs are
| | test-clean | test-other | comment | | | dev | val | comment |
|---------------------------|------------|------------|------------------------------------------| |---------------------------|------------|------------|------------------------------------------|
| greedy search | 2.85 | 6.98 | --epoch 28, --avg 15, --max-duration 100 | | greedy search | 2.46 | 2.40 | --avg-last-n 10 --max-duration 500 |
| beam search | 2.27 | 2.24 | --avg-last-n 10 --max-duration 500 --beam-size 4 |
| modified beam search | 2.34 | 2.30 | --avg-last-n 10 --max-duration 500 --beam-size 4 |
| fast beam search | 2.38 | 2.35 | --avg-last-n 10 --max-duration 500 --beam-size 4 --max-contexts 4 --max-states 8 |
**NOTE:** SPGISpeech transcripts can be prepared in `ortho` or `norm` ways, which refer to whether the
transcripts are orthographic or normalized. These WERs correspond to the normalized transcription
scenario.
The training command for reproducing is given below: The training command for reproducing is given below:
``` ```
export CUDA_VISIBLE_DEVICES="0,1,2,3" export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
./pruned_transducer_stateless/train.py \ ./pruned_transducer_stateless2/train.py \
--world-size 4 \ --world-size 8 \
--num-epochs 30 \ --num-epochs 20 \
--start-epoch 0 \ --start-epoch 0 \
--exp-dir pruned_transducer_stateless/exp \ --exp-dir pruned_transducer_stateless2/exp \
--full-libri 1 \ --max-duration 200 \
--max-duration 300 \
--prune-range 5 \ --prune-range 5 \
--lr-factor 5 \ --lr-factor 5 \
--lm-scale 0.25 \ --lm-scale 0.25 \
--use-fp16 True
``` ```
The tensorboard training log can be found at The tensorboard training log can be found at
@ -36,263 +45,12 @@ The tensorboard training log can be found at
The decoding command is: The decoding command is:
``` ```
epoch=28 ## fast beam search
avg=15
## greedy search
./pruned_transducer_stateless/decode.py \ ./pruned_transducer_stateless/decode.py \
--epoch $epoch \ --avg-last-n 10 \
--avg $avg \
--exp-dir pruned_transducer_stateless/exp \ --exp-dir pruned_transducer_stateless/exp \
--max-duration 100 --max-duration 500 \
--beam-size 4 \
--max-contexts 4 \
--max-states 8
``` ```
### LibriSpeech BPE training results (Transducer)
#### Conformer encoder + embedding decoder
Using commit `a8150021e01d34ecbd6198fe03a57eacf47a16f2`.
Conformer encoder + non-recurrent 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 (max sym per frame 1) | 2.68 | 6.71 | --epoch 61, --avg 18, --max-duration 100 |
| greedy search (max sym per frame 2) | 2.69 | 6.71 | --epoch 61, --avg 18, --max-duration 100 |
| greedy search (max sym per frame 3) | 2.69 | 6.71 | --epoch 61, --avg 18, --max-duration 100 |
| modified beam search (beam size 4) | 2.67 | 6.64 | --epoch 61, --avg 18, --max-duration 100 |
The training command for reproducing is given below:
```
cd egs/librispeech/ASR/
./prepare.sh
export CUDA_VISIBLE_DEVICES="0,1,2,3"
./transducer_stateless/train.py \
--world-size 4 \
--num-epochs 76 \
--start-epoch 0 \
--exp-dir transducer_stateless/exp-full \
--full-libri 1 \
--max-duration 300 \
--lr-factor 5 \
--bpe-model data/lang_bpe_500/bpe.model \
--modified-transducer-prob 0.25
```
The tensorboard training log can be found at
<https://tensorboard.dev/experiment/qgvWkbF2R46FYA6ZMNmOjA/#scalars>
The decoding command is:
```
epoch=61
avg=18
## greedy search
for sym in 1 2 3; do
./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 \
--max-sym-per-frame $sym
done
## modified 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 \
--context-size 2 \
--decoding-method modified_beam_search \
--beam-size 4
```
You can find a pretrained model by visiting
<https://huggingface.co/csukuangfj/icefall-asr-librispeech-transducer-stateless-bpe-500-2022-02-07>
#### Conformer encoder + LSTM decoder
Using commit `8187d6236c2926500da5ee854f758e621df803cc`.
Conformer encoder + LSTM decoder.
The best WER is
| | test-clean | test-other |
|-----|------------|------------|
| WER | 3.07 | 7.51 |
using `--epoch 34 --avg 11` 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 35 \
--start-epoch 0 \
--exp-dir transducer/exp-lr-2.5-full \
--full-libri 1 \
--max-duration 180 \
--lr-factor 2.5
```
The decoding command is:
```
epoch=34
avg=11
./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/D7NQc3xqTpyVmWi5FnWjrA>
### 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:
```bash
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: https://github.com/k2-fsa/icefall/commit/caa0b9e9425af27e0c6211048acb55a76ed5d315
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|

10
egs/spgispeech/ASR/decode.sh
View File

@ -1,10 +0,0 @@
#!/usr/bin/env bash
set -eou pipefail
. ./path.sh
. parse_options.sh || exit 1
# Train Conformer CTC model
utils/queue-freegpu.pl --gpu 1 --mem 10G -l "hostname=c*" -q g.q conformer_ctc/exp/decode.log \
python conformer_ctc/decode.py --epoch 12 --avg 3 --method ctc-decoding --max-duration 50 --num-paths 20

10
egs/spgispeech/ASR/train.sh
View File

@ -1,10 +0,0 @@
#!/usr/bin/env bash
set -eou pipefail
. ./path.sh
. parse_options.sh || exit 1
# Train Conformer CTC model
utils/queue-freegpu.pl --gpu 1 --mem 10G -l "hostname=c2[3-7]*" conformer_ctc/exp/train.log \
python conformer_ctc/train.py --world-size 1