Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

The WER comparison between current benchmark and DS2 paper #93

Closed
kuke opened this issue Dec 21, 2017 · 0 comments
Closed

The WER comparison between current benchmark and DS2 paper #93

kuke opened this issue Dec 21, 2017 · 0 comments

Comments

@kuke
Copy link
Contributor

kuke commented Dec 21, 2017 •
edited
Loading

With the latest update, the BaiduEN8K model has caught up with the original Deep Speech 2 work in WER performance on some public test datasets.

On pubic LM (8.3G) On internal LM (260G) DS2 paper
LibriSpeech Test-Clean 5.41 5.28 5.33
LibriSpeech Test-Other 13.85 13.49 13.26
VoxForge American-Canadian 7.13 6.96 7.55
VoxForge Commonwealth 14.93 14.62 13.56
VoxForge European 18.64 18.34 17.55
VoxForge Indian 25.51 25.27 22.44
  • Training data set: 8628h vs. 11940h
Jackwaterveg pushed a commit to Jackwaterveg/DeepSpeech that referenced this issue Jan 29, 2022
@Xreki
Disbale gc flags for PaddingRNN. (PaddlePaddle#93)
ccf76b5 
* Disbale gc flags for paddingrnn.

* Only disable GC for small model.
Jackwaterveg pushed a commit to Jackwaterveg/DeepSpeech that referenced this issue Jan 29, 2022
@Xreki
Revert "Disbale gc flags for PaddingRNN. (PaddlePaddle#93)" (PaddlePa…
e535318 
…ddle#105)

This reverts commit 69b23a233f43eb1f3398349ece6a0e0f06e55707.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zh794390558 @kuke