用 MOSS-TTS-Local微调后推理出的音频结尾有杂音
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.1k
- Forks
- 373
- Avg merge
- 20m
- Merged PRs (30d)
- 1
Description
项目组你们好：
我用贵项目MOSS-TTS-Local1.7B模型微调后，训练了5轮，音频数据大概1个多小时。在后期推理时，无论选择哪个模型，最终出来的音频的结尾都有杂音（尾影），而且是时有时无，请问这是什么原因？以下附上这个杂音的音频。这个杂音有时大有时弱，有时有，有时无。为了让你们听清楚，我特意加了10遍，时长1秒。
请知悉！
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the attached noise.wav and reproducing inference after five fine-tuning epochs with the reported roughly one-hour dataset. Compare outputs across the available models and document the settings and conditions that produce the intermittent end noise; done means identifying a reproducible cause or narrowing it to a specific inference or training condition.
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
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100