【长期】跨语言支持
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
### 已有讨论
#142
#197
### Q & A
[LxnChan](https://github.com/LxnChan)
有足够的样本的前提下我想自己训练出来一个日语模型,不知道行不行
答:就像把中文句子例如 “你好” 变成 “ni2 hao3”,只需要找到一个tts前端处理一下日语为phenomenon
> 作者却苦于近期精力限制只能势单力薄处理一些小的bug,也看到issue区有不少爱好与开发者想要学习或二次改造更好满足自己需求,不过比较零碎难以展开。为了让项目和AI持续可以给大家提供更多价值,共同学习,我在issue区根据不同主题创建长期交流频道,若留言人数超过20也将建立对应交流群。
> - 如何改参数,搞出更逼真的克隆效果 435
> - 如何改模型,搞出更好效果 436
> - 训练克隆特定人声音&finetune 437
> - 学术/论文讨论/训练分析 438
> - 跨语言支持 440
> - 工程化/新场景讨论(绝不做恶 & 合法合规) 439
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue points to discussions #142 and #197 and mentions training a Japanese model plus a TTS frontend or phoneme conversion, but names no files or tests. Read those linked issues first; completion criteria and an implementation entry point are not defined.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- internationalization, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100