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

update repo (#917)

Browse Source
This commit is contained in:
jmwang66 2023-09-03 21:33:51 +08:00 committed by GitHub
parent a4d0724b27
commit f9f7aab35b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
egs/librispeech/branchformer/README.md Normal file
View File

@ -0,0 +1,16 @@
# Branchformer Result
## Training Config
- Feature info: using raw speech, extracting 80 dims fbank online, global cmvn, speed perturb(0.9, 1.0, 1.1), specaugment
- Train config: conf/train_asr_branchformer.yaml
- LM config: LM was not used
## Results (CER)
- Decode config: conf/decode_asr_transformer_beam10_ctc0.3.yaml (ctc weight:0.3)
| testset | CER(%) |
|:-----------:|:-------:|
| dev_clean | 2.12 |
| dev_other | 5.25 |
| test_clean | 2.34 |
| test_other | 5.39 |

16
egs/librispeech/e_branchformer/README.md Normal file
View File

@ -0,0 +1,16 @@
# Branchformer Result
## Training Config
- Feature info: using raw speech, extracting 80 dims fbank online, global cmvn, speed perturb(0.9, 1.0, 1.1), specaugment
- Train config: conf/train_asr_e_branchformer.yaml
- LM config: LM was not used
## Results (CER)
- Decode config: conf/decode_asr_transformer_beam10_ctc0.3.yaml (ctc weight:0.3)
| testset | CER(%) |
|:-----------:|:-------:|
| dev_clean | 1.97 |
| dev_other | 4.75 |
| test_clean | 2.15 |
| test_other | 4.80 |