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.

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

pytorch 版本和 中文离线文件转写服务(CPU版本)版本识别录音文件 差别巨大 #1722

Closed
zengcmail opened this issue May 12, 2024 · 3 comments

Comments

@zengcmail
Copy link

我们想使用 FunASR 做呼叫中心的 录音质检

发现同一段录音,使用:
funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=测试录音文件.wav
---》
正确率还不错,基本都正确

但是,使用:中文离线文件转写服务(CPU版本)版本的
python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "测试录音文件.wav"
---》
测试效果非常差,完全不正确

请问,这 2 者出现差异,是因为我的配置问题,还是什么问题,如何解决,非常感谢

@lixikun
Copy link

lixikun commented May 13, 2024

先看下你的采样率是否是16K的,采样率一样基本不会有太大的差别

@FD-Liekkas
Copy link

我也遇到过类似的,后来发现是文件采样率和声道数量没对齐,需要是16K并且单声道的音频,你可以转换完再试试

@lyblsgo
Copy link
Collaborator

lyblsgo commented May 28, 2024

Please confirm your audio format; if the issue persists, you can reopen the issue.

@lyblsgo lyblsgo closed this as completed May 28, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants