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

atsr

Browse Source
This commit is contained in:
语帆 2024-03-04 16:48:01 +08:00
parent d9e60d9ddc
commit 9c884c566f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/industrial_data_pretraining/lcbnet/README.md
View File

@ -164,7 +164,7 @@ output_dir/
token：语音识别结果文件
可以使用funasr里面提供的run_bwer_recall.sh计算WER、BWER、UWER和Recall。
详细脚本可以参考funasr里面的demo.sh脚本，需要注意的是你需要修改一下iic/LCB-NET/conf.yaml中CMVN(stats_file)的路径和iic/LCB-NET/dev/wav.scp里面ark的路径，修改为你自己本地的路径，然后跑解码。
## 相关论文以及引用信息