Skip to content

Update benchmark results for LibriSpeech model due to #427 #436

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

Merged
kuke merged 1 commit into from
Nov 8, 2017
Merged

Update benchmark results for LibriSpeech model due to #427 #436

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions deep_speech_2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -498,13 +498,13 @@ Language Model | Training Data | Token-based | Size | Descriptions

Test Set | LibriSpeech Model | BaiduEN8K Model
:--------------------- | ---------------: | -------------------:
LibriSpeech Test-Clean | 8.06 | 6.63
LibriSpeech Test-Other | 24.25 | 16.59
VoxForge American-Canadian | 13.48 |   7.46
VoxForge Commonwealth | 22.37 | 16.23
VoxForge European | 32.64 | 20.47
VoxForge Indian | 58.48 | 28.15
Baidu Internal Testset  |   48.93 |   8.92
LibriSpeech Test-Clean | 7.77 | 6.63
LibriSpeech Test-Other | 23.25 | 16.59
VoxForge American-Canadian | 12.52 |   7.46
VoxForge Commonwealth | 21.08 | 16.23
VoxForge European | 31.21 | 20.47
VoxForge Indian | 56.79 | 28.15
Baidu Internal Testset  |   47.73 |   8.92

#### Benchmark Results for Mandarin Model (Character Error Rate)

Expand Down