使用中文readme中的第三个模型，同样的input音频文件和文字内容，得到的结果音频有杂音且每次效果不同
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
使用中文readme中的第三个模型，同样的input音频文件和文字内容，得到的结果音频有电流音且每次效果不同。
这是哪里的设置会影响到结果生成吗？求告知！
[输入输出音频.zip](https://github.com/babysor/MockingBird/files/9180436/default.zip)
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the third model described in the Chinese README and reproduce the report using the attached input/output audio archive. Inspect the model and inference settings used there, then determine which setting causes electrical noise or run-to-run variation; done means the cause is identified and the same audio and text produce stable, clean output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100