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.

Sign up for GitHub

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

Jump to bottom

希望增加使用Apple本地语音识别功能转换实时字幕 #33

Open
suliveevil opened this issue Dec 15, 2021 · 9 comments
Open

希望增加使用Apple本地语音识别功能转换实时字幕 #33

suliveevil opened this issue Dec 15, 2021 · 9 comments
Assignees
@summershrimp
Labels
enhancement New feature or request

Comments

@suliveevil
Copy link

No description provided.

@suliveevil suliveevil changed the title 希望增加Apple本地语音识别功能转换实时字幕 希望增加使用Apple本地语音识别功能转换实时字幕 Dec 15, 2021
@summershrimp
Copy link
Owner

summershrimp commented Dec 16, 2021 •
edited
Loading

有相关的文档链接么？（而且截止到目前，并没有人赞助本项目一个apple开发者账户，因此如果是涉及到调用apple的speechkit的话，也做不到

@summershrimp summershrimp added enhancement New feature or request question Further information is requested labels Dec 16, 2021
@suliveevil
Copy link
Author

suliveevil commented Dec 16, 2021 •
edited
Loading

只找到了 Apple Create ML 里的 speech framework：https://developer.apple.com/documentation/speech
离线语音转文字/字幕目前好像除了用 Mozilla 的 DeepSpeech就只有 Apple 的speech 可以用了。

@suliveevil
Copy link
Author

补充一个离线语音识别API：https://github.com/alphacep/vosk-api

@summershrimp
Copy link
Owner

vosk这个我可以看一下，苹果的api我这边没有开发者账户，应该是没法直接用

@suliveevil
Copy link
Author

感谢🙏

@summershrimp summershrimp reopened this Feb 21, 2022
@summershrimp summershrimp removed the question Further information is requested label Feb 21, 2022
@summershrimp summershrimp self-assigned this Feb 21, 2022
@suliveevil
Copy link
Author

suliveevil commented Dec 8, 2022 •
edited
Loading

恍惚间已经一年了，终于有了一个离线可用的字幕生成工具：whisper

https://github.com/openai/whisper

也有了别人打包好的 app：

https://github.com/chidiwilliams/buzz

特此分享一下。

@summershrimp
Copy link
Owner

summershrimp commented Dec 8, 2022 via email

@suliveevil
Copy link
Author

suliveevil commented Dec 8, 2022 •
edited
Loading

我只用了一个两小时的英文播客测试了，转录的字幕质量还是非常高的，也有人反馈说对中文支持不是特别好。

https://meta.appinn.net/t/topic/38263

我和家人的通话录音都是方言，就还没用这些工具进行文字化处理。

中文应该还是 macOS 的数据更多模型更好吧，毕竟做了很多年的无障碍功能。
App Store 里也有实现了实时字幕的 App：

Be My Ears - Mac App Store

@summershrimp
Copy link
Owner

summershrimp commented Dec 9, 2022 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@summershrimp summershrimp

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@summershrimp @suliveevil