关于synthesizer的疑问
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
大佬们，如果我只是想针对性模仿一个人的声音，能否训练一个只有那个人的synthesizer模型，如果可以的话大概需要多少的数据量。因为试过issue里260k的aidatatang_200zh的model感觉效果还是一般。
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points and asks an open-ended question about training a speaker-specific synthesizer and required data. Before work can begin, identify the relevant synthesizer training entry point and define measurable training-data and quality goals.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100