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

语音识别时能否保留数字 #2481

Open
dsyrock opened this issue Sep 28, 2022 · 9 comments
Open

语音识别时能否保留数字 #2481

dsyrock opened this issue Sep 28, 2022 · 9 comments
Assignees

Comments

@dsyrock
Copy link

dsyrock commented Sep 28, 2022

我看文档里有写到这一项功能

Supported NSW (Non-Standard-Word) Normalization

但如果我不希望全部转成中文,想保留数字形式的话,这个能实现吗?

@yaleimeng
Copy link

这一块确实很不方便。。市面上的语音识别产品大部分都是数字优先,而不是全汉字优先。
遇到统计数字比较多的段落,识别完再一个个手工处理特别费事。

@yt605155624
Copy link
Collaborator

yt605155624 commented Sep 29, 2022

不好意思,Supported NSW (Non-Standard-Word) Normalization 是 TTS 文本前端的能力,表示 TN (文本正则),用户输入数字等非标准词也可以正确读出来,对应到 ASR 里面应该是 ITN(反文本正则),把标准词转为数字等非标准词,目前还没有

@SmileGoat
Copy link
Contributor

ITN排期ing,会做这个模块,maybe 3 month later

@dsyrock
Copy link
Author

dsyrock commented Sep 29, 2022

感谢两位!

@yaleimeng
Copy link

我们可以自己写个后处理先用着。。以前在github似乎也见过相关的开源代码。

@stale
Copy link

stale bot commented Nov 22, 2022

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

@stale stale bot added the Stale label Nov 22, 2022
@stale
Copy link

stale bot commented Dec 23, 2022

This issue is closed. Please re-open if needed.

@stale stale bot closed this as completed Dec 23, 2022
@yt605155624 yt605155624 reopened this Dec 28, 2022
@yt605155624 yt605155624 removed the Stale label Dec 28, 2022
@1547481339
Copy link

请问解决了吗?我现在使用,识别结果还是汉字

@yaleimeng
Copy link

有需要的话自己做后处理。全汉字输出也没太大问题。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

6 participants