Skip to content

D
DeepSpeech

PaddlePaddle / DeepSpeech
1 年多 前同步成功

通知 207
Star 8425
Fork 1598
D
DeepSpeech
提交 b10af168 编写于 作者: H Hui Zhang
浏览文件
操作

update librispeech transformer test w/o length filter of test clean

上级 13a4bee8
隐藏空白更改
内联 并排
Showing with 6 addition and 4 deletion
examples/librispeech/s1/README.md
浏览文件 @ b10af168
......@@ -31,6 +31,8 @@
## Transformer
### Test w/ 20s length filter
| Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER |
| --- | --- | --- | --- | --- | --- | --- | --- |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean | attention | 6.98 | 0.036 |
......@@ -38,7 +40,7 @@
### Test w/o length filter
| Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER |
| --- | --- | --- | --- | --- | --- | --- | --- |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | attention | 7.63 | 0.056832 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | ctc_greedy_search | 7.63 | 0.059742 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | ctc_prefix_beam_search | 7.63 | 0.059057 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | attention_rescoring | 7.63 | 0.047417 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | attention | 7.404532432556152 | 0.056204 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | ctc_greedy_search | 7.404532432556152 | 0.058658 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | ctc_prefix_beam_search | 7.404532432556152 | 0.058278 |
| transformer | 32.52 M | conf/transformer.yaml | spec_aug + shift | test-clean-all | attention_rescoring | 7.404532432556152 | 0.045591 |
Markdown is supported
0% 或 .
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 或