Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,94 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: unknown
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: unknown
|
| 3 |
+
---
|
| 4 |
+
# miotts-cpp-gguf (for mio-tts-cpp)
|
| 5 |
+
|
| 6 |
+
`mio-tts-cpp`(C++/llama.cpp ベース)で **MioTTS 推論**を行うための GGUF/補助ファイル一式です。
|
| 7 |
+
収録物は **上流(Aratako さん)モデル**を元に、`mmnga-o` が **配布・変換・同梱**しています。
|
| 8 |
+
|
| 9 |
+
## 対応アプリ / リポジトリ
|
| 10 |
+
- 推論アプリ(C++): https://github.com/mmnga/mio-tts-cpp (MIT License)
|
| 11 |
+
- 参考(上流の推論/付帯物): https://github.com/Aratako/MioTTS-Inference (MIT License)
|
| 12 |
+
|
| 13 |
+
## 含まれるファイル(作者・出典・ライセンス)
|
| 14 |
+
|
| 15 |
+
> 注意: この Hugging Face リポジトリ自体の License 表示が `unknown` のため、**各ファイルは上流のライセンスに従います**。
|
| 16 |
+
> https://huggingface.co/mmnga-o/miotts-cpp-gguf
|
| 17 |
+
|
| 18 |
+
| ファイル | 役割 | 作者/出典 | ライセンス/注意 |
|
| 19 |
+
|---|---|---|---|
|
| 20 |
+
| `MioTTS-0.1B-Q8_0.gguf` | TTS LLM 本体(0.1B / GGUF) | https://huggingface.co/Aratako/MioTTS-0.1B | **Falcon-LLM License**(上流に従う) |
|
| 21 |
+
| `miocodec.gguf` | ボコーダ/音声コーデック(24kHz 系) | https://huggingface.co/Aratako/MioCodec-25Hz-24kHz | **MIT License**(上流に従う) |
|
| 22 |
+
| `miocodec-24khz.gguf` | 24kHz 系ボコーダ別ビルド | 本リポジトリ同梱 | **要確認**(上流ライセンス継承の想定。配布側で明記推奨) |
|
| 23 |
+
| `miocodec-25hz-44k-v2.gguf` | 44.1kHz 系ボコーダ別ビルド | 本リポジトリ同梱 | **要確認**(上流ライセンス継承の想定。配布側で明記推奨) |
|
| 24 |
+
| `en_female.emb.gguf` / `en_male.emb.gguf` / `jp_female.emb.gguf` / `jp_male.emb.gguf` | プリセット話者埋め込み | 本リポジトリ同梱 | **要確認**:生成元(参照音声/モデル)により利用条件が変わり得ます。上流 `MioTTS-Inference` にはプリセット音声に関する注意が記載されています。 |
|
| 25 |
+
|
| 26 |
+
## 使い方(例)
|
| 27 |
+
|
| 28 |
+
```bash
|
| 29 |
+
./build/llama-tts-mio \
|
| 30 |
+
-m models/MioTTS-0.1B-Q8_0.gguf \
|
| 31 |
+
-mv models/miocodec.gguf \
|
| 32 |
+
-emb models/jp_female.emb.gguf \
|
| 33 |
+
-p "こんにちは、今日はいい天気ですね。" \
|
| 34 |
+
-o out.wav
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## クレジット
|
| 38 |
+
- MioTTS-0.1B: Aratako(Falcon-LLM License)
|
| 39 |
+
https://huggingface.co/Aratako/MioTTS-0.1B
|
| 40 |
+
- MioCodec-25Hz-24kHz: Aratako(MIT)
|
| 41 |
+
https://huggingface.co/Aratako/MioCodec-25Hz-24kHz
|
| 42 |
+
- mio-tts-cpp(推論アプリ): mmnga(MIT)
|
| 43 |
+
https://github.com/mmnga/mio-tts-cpp
|
| 44 |
+
|
| 45 |
+
## 免責
|
| 46 |
+
本リポジトリは変換/同梱物を含みます。**利用時は各上流モデル/付帯物のライセンス・利用条件に従ってください**。
|
| 47 |
+
特に埋め込み(`.emb.gguf`)などのプリセット類は、生成元次第で制限が変わる可能性があります。
|
| 48 |
+
|
| 49 |
+
---
|
| 50 |
+
|
| 51 |
+
# miotts-cpp-gguf (for mio-tts-cpp) — English
|
| 52 |
+
|
| 53 |
+
A bundle of GGUF + auxiliary files for running **MioTTS inference** with `mio-tts-cpp` (C++/llama.cpp-based).
|
| 54 |
+
Contents are based on upstream work by **Aratako**, packaged/converted and redistributed by `mmnga-o`.
|
| 55 |
+
|
| 56 |
+
## Related repositories
|
| 57 |
+
- Inference app (C++): https://github.com/mmnga/mio-tts-cpp (MIT License)
|
| 58 |
+
- Upstream inference utilities / assets reference: https://github.com/Aratako/MioTTS-Inference (MIT License)
|
| 59 |
+
|
| 60 |
+
## Included files (author, source, license)
|
| 61 |
+
|
| 62 |
+
> Note: This Hugging Face repo shows License = `unknown`, so **each file follows its upstream license/terms**.
|
| 63 |
+
> https://huggingface.co/mmnga-o/miotts-cpp-gguf
|
| 64 |
+
|
| 65 |
+
| File | Purpose | Author / Source | License / Notes |
|
| 66 |
+
|---|---|---|---|
|
| 67 |
+
| `MioTTS-0.1B-Q8_0.gguf` | Main TTS model (0.1B / GGUF) | https://huggingface.co/Aratako/MioTTS-0.1B | **Falcon-LLM License** (follow upstream) |
|
| 68 |
+
| `miocodec.gguf` | Vocoder / audio codec (24kHz) | https://huggingface.co/Aratako/MioCodec-25Hz-24kHz | **MIT License** (follow upstream) |
|
| 69 |
+
| `miocodec-24khz.gguf` | 24kHz codec build variant | bundled in this repo | **TBD** (expected to inherit upstream; explicitly document when distributing) |
|
| 70 |
+
| `miocodec-25hz-44k-v2.gguf` | 44.1kHz codec build variant | bundled in this repo | **TBD** (expected to inherit upstream; explicitly document when distributing) |
|
| 71 |
+
| `en_female.emb.gguf` / `en_male.emb.gguf` / `jp_female.emb.gguf` / `jp_male.emb.gguf` | Preset speaker embeddings | bundled in this repo | **TBD**: terms may depend on how embeddings were produced. Upstream `MioTTS-Inference` includes caveats around preset audio/assets. |
|
| 72 |
+
|
| 73 |
+
## Usage (example)
|
| 74 |
+
|
| 75 |
+
```bash
|
| 76 |
+
./build/llama-tts-mio \
|
| 77 |
+
-m models/MioTTS-0.1B-Q8_0.gguf \
|
| 78 |
+
-mv models/miocodec.gguf \
|
| 79 |
+
-emb models/jp_female.emb.gguf \
|
| 80 |
+
-p "Hello! This is a test." \
|
| 81 |
+
-o out.wav
|
| 82 |
+
```
|
| 83 |
+
|
| 84 |
+
## Credits
|
| 85 |
+
- MioTTS-0.1B: Aratako (Falcon-LLM License)
|
| 86 |
+
https://huggingface.co/Aratako/MioTTS-0.1B
|
| 87 |
+
- MioCodec-25Hz-24kHz: Aratako (MIT)
|
| 88 |
+
https://huggingface.co/Aratako/MioCodec-25Hz-24kHz
|
| 89 |
+
- mio-tts-cpp (inference app): mmnga (MIT)
|
| 90 |
+
https://github.com/mmnga/mio-tts-cpp
|
| 91 |
+
|
| 92 |
+
## Disclaimer
|
| 93 |
+
This repo contains converted/bundled artifacts. **Please comply with upstream licenses and usage terms** for each file.
|
| 94 |
+
Preset embeddings (`.emb.gguf`) and other assets may have additional constraints depending on how they were created.
|