speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

add paraformer_large_online RESULTS.md

Browse Source
This commit is contained in:
北念 2023-08-03 20:27:27 +08:00
parent 56440842b6
commit e01ea43dde
1 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/RESULTS.md Normal file
View File

@ -0,0 +1,38 @@
# Paraformer-Large
- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary>
- Model size: 220M
# Beachmark Results
## AISHELL-1
- Decode config:
- Decode without CTC
- Decode without LM
| CER(%) | Pretrain model|
|:---------:|:-------------:|
| dev | 2.37 |
| test | 3.34 |
## AISHELL-2
- Decode config:
- Decode without CTC
- Decode without LM
| CER(%) | Pretrain model|
|:------------:|:-------------:|
| dev_ios | 4.04 |
| test_android | 3.86 |
| test_ios | 4.38 |
| test_mic | 4.21 |
## Wenetspeech
- Decode config:
- Decode without CTC
- Decode without LM
| testset | CER(%)|
|:---------:|:-----:|
| dev | 4.55 |
| test | 10.64 |
| test_net | 7.78 |