feat: Integrate IndexTTS2 model and update related schemas and frontend components
This commit is contained in:
32
README.zh.md
32
README.zh.md
@@ -13,7 +13,8 @@
|
||||
- 自定义语音:预定义说话人语音
|
||||
- 语音设计:自然语言描述创建语音
|
||||
- 语音克隆:上传音频克隆语音
|
||||
- 有声书生成:上传 EPUB 文件,通过 LLM 自动提取角色并分配语音,生成多角色有声书
|
||||
- **IndexTTS2**:高质量语音克隆,支持情感控制(高兴、愤怒、悲伤、恐惧、惊讶等),由 [IndexTTS2](https://github.com/iszhanjiawei/indexTTS2) 驱动
|
||||
- 有声书生成:上传 EPUB 文件,通过 LLM 自动提取角色并分配语音,生成多角色有声书;支持为每个角色单独启用 IndexTTS2
|
||||
- 双后端支持:支持本地模型和阿里云 TTS API 切换
|
||||
- 多语言支持:English、简体中文、繁體中文、日本語、한국어
|
||||
- JWT 认证、异步任务、语音缓存、暗黑模式
|
||||
@@ -148,6 +149,25 @@ hf download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-0.
|
||||
hf download Qwen/Qwen3-TTS-12Hz-0.6B-Base --local-dir ./Qwen3-TTS-12Hz-0.6B-Base
|
||||
```
|
||||
|
||||
**IndexTTS2 模型(可选,用于情感控制语音克隆)**
|
||||
|
||||
IndexTTS2 是可选功能。如需使用,在同一 `Qwen/` 目录下运行:
|
||||
|
||||
```bash
|
||||
# 仅下载所需文件,无需下载完整仓库
|
||||
hf download IndexTeam/IndexTTS-2 \
|
||||
bpe.model config.yaml feat1.pt feat2.pt gpt.pth s2mel.pth wav2vec2bert_stats.pt \
|
||||
--local-dir ./IndexTTS2
|
||||
```
|
||||
|
||||
然后安装 indextts 包:
|
||||
```bash
|
||||
git clone https://github.com/iszhanjiawei/indexTTS2.git
|
||||
cd indexTTS2
|
||||
pip install -e . --no-deps
|
||||
cd ..
|
||||
```
|
||||
|
||||
**最终目录结构:**
|
||||
|
||||
Docker 部署(`docker/models/`):
|
||||
@@ -169,7 +189,15 @@ Qwen3-TTS-webUI/
|
||||
├── Qwen3-TTS-Tokenizer-12Hz/
|
||||
├── Qwen3-TTS-12Hz-1.7B-CustomVoice/
|
||||
├── Qwen3-TTS-12Hz-1.7B-VoiceDesign/
|
||||
└── Qwen3-TTS-12Hz-1.7B-Base/
|
||||
├── Qwen3-TTS-12Hz-1.7B-Base/
|
||||
└── IndexTTS2/ ← 可选,用于 IndexTTS2 功能
|
||||
├── bpe.model
|
||||
├── config.yaml
|
||||
├── feat1.pt
|
||||
├── feat2.pt
|
||||
├── gpt.pth
|
||||
├── s2mel.pth
|
||||
└── wav2vec2bert_stats.pt
|
||||
```
|
||||
|
||||
### 3. 后端配置
|
||||
|
||||
Reference in New Issue
Block a user