Skip to content

D
DeepSpeech

PaddlePaddle / DeepSpeech
12 个月 前同步成功

通知 205
Star 8425
Fork 1598
D
DeepSpeech

体验新版 GitCode，发现更多精彩内容 >>

未验证 提交 9d28f86d 编写于 作者: J Junkun Chen 提交者： GitHub
浏览文件
操作

update timit result, test=doc_fix (#1147)

上级 9ff12d3f
隐藏空白更改
内联 并排
Showing with 5 addition and 5 deletion
examples/timit/asr1/RESULTS.md
浏览文件 @ 9d28f86d
......@@ -3,7 +3,7 @@
### Transformer
| Model | Params | Config | Decode method | Loss | PER |
| --- | --- | --- | --- | --- | --- |
| transformer | 5.17M | conf/transformer.yaml | attention | 46.41119385 | 0.469993 |
| transformer | 5.17M | conf/transformer.yaml | ctc_greedy_search | 46.41119385 | 0.297713 |
| transformer | 5.17M | conf/transformer.yaml | ctc_prefix_beam_search | 46.41119385 | 0.293555 |
| transformer | 5.17M | conf/transformer.yaml | attention_rescore | 46.41119385 | 0.281081 |
| transformer | 5.17M | conf/transformer.yaml | attention | 46.41119385 | 0.396950 |
| transformer | 5.17M | conf/transformer.yaml | ctc_greedy_search | 46.41119385 | 0.182259 |
| transformer | 5.17M | conf/transformer.yaml | ctc_prefix_beam_search | 46.41119385 | 0.188080 |
| transformer | 5.17M | conf/transformer.yaml | attention_rescore | 46.41119385 | 0.184199 |
examples/timit/asr1/conf/transformer.yaml
浏览文件 @ 9d28f86d
......@@ -71,7 +71,7 @@ model:
training:
n_epoch: 200
n_epoch: 50
accum_grad: 1
global_grad_clip: 5.0
optim: adam
......
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