Downloads · 30 days
0
CinixChen/Zhiyan
Zhiyan is a text-to-speech model from CinixChen. Use it when you need text read aloud. It is set up for vits. The card lists the license as other.
A specialized TTS model for reconstructing Middle Chinese phonology.
Downloads · 30 days
0
Access
Public
Updated Aug 21, 2026
Repo size
240 MB
Likes
2
Public
Click a slice to open those files.
.onnx240 MB · 99%
From the Hugging Face model README
A specialized TTS model for reconstructing Middle Chinese phonology.
Zhiyan (廌言) is a text-to-speech (TTS) model based on the International Phonetic Alphabet (IPA), designed to generate high-quality reconstructed audio of Middle Chinese (Qieyun phonological system).
This repository contains multiple versions of the model, trained using the same dataset but with different training strategies.
Zhiyan/
├── v1.2/
│ ├── zhiyan_v1.2.onnx
│ └── zhiyan_v1.2.json
├── v1.3/
│ ├── zhiyan_v1.3.onnx
│ └── zhiyan_v1.3.json
├── symbols.py
├── dictionary.txt
├── LICENSE
└── README.md
Before inference:
symbols.py in vits2_pytorch with the one provided in this repositoryThe ONNX model and config usage are the same as in vits2_pytorch. Please refer to the original project for details.
Example:
python infer_onnx.py \
--model="zhiyan_v1.2.onnx" \
--config-path="configs/zhiyan_v1.2.json" \
--output-wav-path="output.wav" \
--text="«ʈʉuŋ kó hɑ̌n ŋɨə́ , ŋɨə́ ʔịm ɦəp ʥiaŋ .»"
Corresponding Chinese text: 中古漢語,語音合成。
« and end with »Allowed characters:
,.abdeghijklmnopstuwyzŋɑɕɖəɦɨɲɳʂʈʉʐʑʔʣʥʦʨʰʷ́̌ạẹịọỵꭦꭧ
dictionary.txt contains over 26,000 Chinese characters with:
You can use the model for free via the official service:
This model is released under Qieyun TTS Model License v2.1 (custom license).
✅ Inference and audio generation allowed
❌ No model training or fine-tuning
❌ No dataset creation
❌ No API, SaaS, or commercial deployment
For commercial licensing, please contact the author.
See LICENSE for full terms.
For licensing or commercial use:
Provided "as is" without warranty. The author is not liable for any damages.
一個用於重建中古漢語語音的專用 TTS 模型。
廌言(Zhiyan)是一個基於國際音標(IPA)的語音合成(TTS)模型,旨在生成高品質的中古漢語(切韻音系)重建語音。
本倉庫包含多個模型版本,這些模型使用相同數據集訓練,但採用了不同的訓練策略。
Zhiyan/
├── v1.2/
│ ├── zhiyan_v1.2.onnx
│ └── zhiyan_v1.2.json
├── v1.3/
│ ├── zhiyan_v1.3.onnx
│ └── zhiyan_v1.3.json
├── symbols.py
├── dictionary.txt
├── LICENSE
└── README.md
推理前:
symbols.py 替換 vits2_pytorch 原有文件ONNX 模型與 config 的使用方式與 vits2_pytorch 相同,請參考原項目說明。
示例:
python infer_onnx.py \
--model="zhiyan_v1.2.onnx" \
--config-path="configs/zhiyan_v1.2.json" \
--output-wav-path="output.wav" \
--text="«ʈʉuŋ kó hɑ̌n ŋɨə́ , ŋɨə́ ʔịm ɦəp ʥiaŋ .»"
對應漢字:中古漢語,語音合成。
« 開頭,以 » 結尾允許字符:
,.abdeghijklmnopstuwyzŋɑɕɖəɦɨɲɳʂʈʉʐʑʔʣʥʦʨʰʷ́̌ạẹịọỵꭦꭧ
dictionary.txt 包含超過 26,000 個漢字,內容包括:
可通過官方服務免費體驗:
本模型依據 Qieyun TTS Model License v2.1(自訂授權協議)發佈。
✅ 允許 進行推理(Inference)與音頻生成
❌ 禁止 進行模型訓練或微調(Fine-tuning)
❌ 禁止 用於建立數據集
❌ 禁止 用於 API、SaaS 或任何商業化部署
如需商業授權,請聯繫作者。
詳見 LICENSE 文件。
授權或商業合作請聯繫:
本項目按「現狀」提供,不附帶任何保證。作者不對任何損失承擔責任。