| Note: This recipe is trained with the codes from this PR https://github.com/k2-fsa/icefall/pull/349 | |
| # Pre-trained Transducer-Stateless2 models for the WenetSpeech dataset with icefall. | |
| The model was trained on the L subset of WenetSpeech with the scripts in [icefall](https://github.com/k2-fsa/icefall) based on the latest version k2. | |
| ## Training procedure | |
| The main repositories are list below, we will update the training and decoding scripts with the update of version. | |
| k2: https://github.com/k2-fsa/k2 | |
| icefall: https://github.com/k2-fsa/icefall | |
| lhotse: https://github.com/lhotse-speech/lhotse | |
| * Install k2 and lhotse, k2 installation guide refers to https://k2.readthedocs.io/en/latest/installation/index.html, lhotse refers to https://lhotse.readthedocs.io/en/latest/getting-started.html#installation. I think the latest version would be ok. And please also install the requirements listed in icefall. | |
| * Clone icefall(https://github.com/k2-fsa/icefall) and check to the commit showed above. | |
| ``` | |
| git clone https://github.com/k2-fsa/icefall | |
| cd icefall | |
| ``` | |
| * Preparing data. | |
| ``` | |
| cd egs/wenetspeech/ASR | |
| bash ./prepare.sh | |
| ``` | |
| * Training | |
| ``` | |
| export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" | |
| ./pruned_transducer_stateless2/train.py \ | |
| --world-size 8 \ | |
| --num-epochs 15 \ | |
| --start-epoch 0 \ | |
| --exp-dir pruned_transducer_stateless2/exp \ | |
| --lang-dir data/lang_char \ | |
| --max-duration 180 \ | |
| --valid-interval 3000 \ | |
| --model-warm-step 3000 \ | |
| --save-every-n 8000 \ | |
| --training-subset L | |
| ``` | |
| ## Evaluation results | |
| The decoding results (WER%) on WenetSpeech(dev, test-net and test-meeting) are listed below, we got this result by averaging models from epoch 9 to 10. | |
| The WERs are | |
| | | dev | test-net | test-meeting | comment | | |
| |------------------------------------|-------|----------|--------------|------------------------------------------| | |
| | greedy search | 7.80 | 8.75 | 13.49 | --epoch 10, --avg 2, --max-duration 100 | | |
| | modified beam search (beam size 4) | 7.76 | 8.71 | 13.41 | --epoch 10, --avg 2, --max-duration 100 | | |
| | fast beam search (1best) | 7.94 | 8.74 | 13.80 | --epoch 10, --avg 2, --max-duration 1500 | | |
| | fast beam search (nbest) | 9.82 | 10.98 | 16.37 | --epoch 10, --avg 2, --max-duration 600 | | |
| | fast beam search (nbest oracle) | 6.88 | 7.18 | 11.77 | --epoch 10, --avg 2, --max-duration 600 | | |
| | fast beam search (nbest LG) | 14.94 | 16.14 | 22.93 | --epoch 10, --avg 2, --max-duration 600 | | |