yovoice GGUF Model Packages
English · 简体中文
This repository has GGUF model packages for yovoice that are not in the official audio.cpp model repository. Each package runs with the audio.cpp inference engine. The same files are mirrored on Hugging Face and ModelScope.
You don't need to download these files by hand. yovoice downloads them from Settings › Models (or yovoice models download <id>) and checks the size and SHA256 of each file.
Packages
| yovoice model ID | File | Size | SHA256 | Original model | License |
|---|---|---|---|---|---|
kokoro-1.1-zh-q8 | Kokoro-82M-GGUF/kokoro-82m-1.1-zh-multilingual-q8_0.gguf | 255,319,008 bytes | 44d58f231606d7cb9c17eee649ed195a680f356de368068d03a83d9f188ec9c7 | hexgrad/Kokoro-82M-v1.1-zh | Apache-2.0 |
Kokoro-82M 1.1-zh Q8_0
- 103 built-in voices: 100 Chinese voices and 3 English voices (
af_maple,af_sol,bf_vale). No reference audio or voice cloning. - Languages: Chinese, American English, British English. Experimental.
- Includes word-level Chinese pronunciation tables made with the official Misaki frontend, so inference runs without Python.
- Bundled resources and licenses (copies are inside the GGUF under
licenses/): eSpeak-ng data (GPL-3.0-or-later), Misaki (Apache-2.0), jieba (MIT), pypinyin (MIT).
The file was converted with scripts/prepare-kokoro-models.py and the audio.cpp v0.7.4 converter. With Python 3.12, misaki[zh] 0.9.4, jieba 0.42.1, pypinyin 0.55.0, espeakng-loader 0.2.4 and gguf 0.19.0 you get the same SHA256:
python scripts/prepare-kokoro-models.py --source Kokoro-82M-v1.1-zh --audio-cpp audio.cpp --output out --version 1.1-zh
License
Each GGUF file is a converted form of its original model. Use and redistribution are governed by the original model's license listed above and by the licenses of any bundled resources. Please review the original model card and license terms before using or redistributing any converted weights.
简体中文
本仓库存放 yovoice 使用、但 audio.cpp 官方模型仓库 没有提供的 GGUF 模型包，均由 audio.cpp 推理引擎运行。Hugging Face 与 ModelScope 上的文件完全相同。
一般不需要手动下载：在 yovoice 的 设置 › 模型 中下载（或运行 yovoice models download <id>），应用会自动校验文件大小和 SHA256。
模型包
| yovoice 模型 ID | 文件 | 大小 | 原始模型 | 许可 |
|---|---|---|---|---|
kokoro-1.1-zh-q8 | Kokoro-82M-GGUF/kokoro-82m-1.1-zh-multilingual-q8_0.gguf | 255,319,008 字节 | hexgrad/Kokoro-82M-v1.1-zh | Apache-2.0 |
Kokoro-82M 1.1-zh Q8_0
- 103 个内置音色：100 个中文音色和 3 个英文音色（
af_maple、af_sol、bf_vale），不需要参考音频，不支持音色克隆。 - 支持中文、美式英语和英式英语，实验性。
- 内置用官方 Misaki 前端制作的中文词级读音表，推理时不需要 Python。
- 内嵌资源及许可（GGUF 内
licenses/目录附有原文）：eSpeak-ng 数据（GPL-3.0-or-later）、Misaki（Apache-2.0）、jieba（MIT）、pypinyin（MIT）。
文件由 scripts/prepare-kokoro-models.py 调用 audio.cpp v0.7.4 转换器生成。使用 Python 3.12、misaki[zh] 0.9.4、jieba 0.42.1、pypinyin 0.55.0、espeakng-loader 0.2.4、gguf 0.19.0 可得到相同的 SHA256。
许可
每个 GGUF 文件都是原始模型的转换版本，使用和再分发遵循上表所列原始模型的许可以及内嵌资源各自的许可。使用或再分发前请阅读原始模型卡与许可条款。