提交 7992aa66 编写于 作者: H Hui Zhang

update librispeech asr1 transformer result

上级 0818c160
......@@ -19,9 +19,12 @@
## Transformer
train: Epoch 120, 4 V100-32G, 27 Day, avg: 10
| Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER |
| --- | --- | --- | --- | --- | --- | --- | --- |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention | 6.484564081827799 | 0.044355 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_greedy_search | 6.484564081827799 | 0.050479 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_prefix_beam_search | 6.484564081827799 | 0.049890 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention_rescoring | 6.484564081827799 | 0.039200 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention | 6.382194232940674 | 0.049661 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_greedy_search | 6.382194232940674 | 0.049566 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | ctc_prefix_beam_search | 6.382194232940674 | 0.049585 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug | test-clean | attention_rescoring | 6.382194232940674 | 0.038135 |
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册