MOSS-TTS-Local 如何使用固定的speaker来合成音频呢？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.1k
- Forks
- 373
- Avg merge
- 20m
- Merged PRs (30d)
- 1
Description
现在我有3个说话人的数据，我想通过微调的方式使得MOSS-TTS-Local模型能够学会这三个人的音色和韵律，然后推理的时候通过输入指定的speaker id来合成音频，请问该如何做呢？
如何区分多说话人呢？除了采用zero-shot的方式，有比如像CosyVoice3这种通过system prompt来设定的方式吗？
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
Review the MOSS-TTS-Local fine-tuning and inference entry points, focusing on speaker IDs, multi-speaker data, zero-shot use, and the system-prompt approach mentioned in the issue. Determine whether fixed-speaker synthesis is supported and document or scope the required workflow, including what a successful inference result should demonstrate.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100