Indic-Mio
此 Soniqo 页面记录本地 speech-swift / speech-core 实现中的 Indic-Mio。Hugging Face 包链接放在集成说明之后。
先进入站内页面
首页卡片和文档菜单先指向这里;源模型和权重包链接仍在本页提供。
概览
| 模型 | Indic-Mio |
|---|---|
| 用途 | Hindi / Indic emotion TTS with optional reference voice conditioning |
| 后端 | MLX fp16 |
| 输出 | 24 kHz mono waveform |
| 语言 | Hindi / Indic text focus |
| 许可证 | Bundle-specific; verify upstream terms before commercial use |
| 状态 | Programmatic SpeechGenerationModel runtime |
| 来源 | Indic-Mio bundle |
| Swift 产品 | IndicMioTTS |
| CLI / 运行时 | Programmatic runtime; server-side loader support is present |
使用
下面的片段对应当前 speech-swift 仓库暴露的 API 或命令。
import IndicMioTTS
let model = try await IndicMioTTSModel.fromPretrained()
let pcm = try await model.generate(
text: "नमस्ते <happy>",
language: "hi"
)
模型链接
实现说明
- Download requests the primary model, tokenizer/chat files, and miocodec component explicitly; the optional WavLM reference encoder is fetched separately when cloning is used.
- Supported emotion markers are <happy>, <sad>, <angry>, <disgust>, <fear>, and <surprise>.
- MioCodec uses 25 Hz content tokens and decodes to 24 kHz audio.
- Reference cloning extracts a 128-float global embedding through the WavLM reference encoder path.