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

Belle-whisper-large-v3-zh-punct 请问模型是否支持中英文。增强了中文,原有的英文能力还在吗。 #590

Open
zhaowenjun333 opened this issue Sep 29, 2024 · 2 comments

Comments

@zhaowenjun333
Copy link

zhaowenjun333 commented Sep 29, 2024

server 启动

python infer_server_stream.py --host=0.0.0.0 --port=5000 --model_path=/models/Belle-whisper-large-v3-zh-punct-finetune-ct2/

client 测试

python test_stream.py  # 内容为你写的流式测试脚本。

期待得到这样的输出:

{'result': '我的爱好是阅读和听音乐', 'start': 0.0, 'end': 1.82}
{'result': 'My hobby is reading and listening to music', 'start': 1.82, 'end': 4.92}
{'result': '最近我读了一本很有趣的书', 'start': 4.92, 'end': 7.34}
{'result': 'Recently I read a very interesting book', 'start': 7.34, 'end': 10.22}

但是只有中文的,英文的丢失:
{'result': '我的爱好是阅读和听音乐。最近我读了一本很有趣的书。', 'start': 0.0, 'end': 10.22}

请问怎么把英文也加上。

@PL-FE
Copy link

PL-FE commented Oct 24, 2024

我使用了语音转文字,语音中英文结尾的内容直接被忽略了。有5秒左右的英文。这个模型虽然增强了中文,是不是弱化了英文甚至忽略?

@shuaijiang
Copy link
Collaborator

set --language None maybe helpful

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

3 participants