You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Supertonic-ZH weights are provided under an EVALUATION LICENSE. This build is NON-COMMERCIAL ONLY, because its training data includes the Baker/CSMSC corpus (which is licensed for non-commercial use only). By requesting access you agree to: (1) the BigScience Open RAIL-M use-based restrictions that govern the base Supertonic-3 model, and (2) non-commercial use only for this build. A Baker-free build eligible for commercial licensing is available separately — contact the author. This model is a derivative of Supertone/supertonic-3 and is distributed under the same OpenRAIL-M license. Users must review and comply with the upstream license and its use-based restrictions.

🗣️ Supertonic-ZH — v0.1.0-preview

Unofficial Mandarin (Chinese) text-to-speech · built on Supertonic-3.

Supertonic-3 is a fast, lightweight, on-device TTS family that does not synthesize Mandarin out of the box. Supertonic-ZH ships Mandarin as optimized, fused ONNX graphs (text encoder / duration predictor / vector estimator) that run in pure ONNX Runtime — no PyTorch. The vocoder is the frozen, unmodified upstream Supertonic-3 graph.

🔊 Hear it first — demos + benchmark: github.com/wuxuedaifu/supertonic_cn (Mandarin, plus retained English / Russian / Arabic / French / Japanese / Korean from the base model).

🔐 Gated / access

These weights are gated and provided on request under an evaluation license. Click "Request access" above. The current build is non-commercial only (Baker/CSMSC training data). Commercial licensing (a Baker-free build) is available separately — contact the author.

📦 What's in this repo

File	What it is
`text_encoder_zh.onnx`	Mandarin text encoder (fused / optimized ONNX)
`duration_predictor_zh.onnx`	Mandarin duration predictor (fused / optimized ONNX)
`vector_estimator_zh.onnx`	Mandarin flow / vector estimator (fused / optimized ONNX)
`unicode_indexer_zh.json`	Chinese Unicode tokenizer / vocabulary
`voice_zh.json`	Preset Mandarin voice (style embedding)
`example_infer.py`	Minimal pure–ONNX Runtime inference example

Not included — obtain from upstream:

vocoder.onnx — the frozen base vocoder, from the upstream Supertone/supertonic-3 release (OpenRAIL-M).

Usage

1. Request access

Open this repository on HF Mirror, review the license conditions, and click Request access.

This release is for evaluation and non-commercial use only.

2. Install dependencies

pip install huggingface_hub onnxruntime numpy soundfile

For NVIDIA GPU inference, install ONNX Runtime GPU instead:

pip install huggingface_hub onnxruntime-gpu numpy soundfile

Do not install both onnxruntime and onnxruntime-gpu in the same environment.

3. Authenticate with HF Mirror

hf auth login

Use a HF Mirror access token belonging to an account that has been granted access to this repository.

4. Download Supertonic-ZH

hf download dove88/supertonic-zh \
  --local-dir ./supertonic-zh

Alternatively, download it from Python:

from huggingface_hub import snapshot_download

model_dir = snapshot_download(
    repo_id="dove88/supertonic-zh",
    local_dir="./supertonic-zh",
)

print(f"Model downloaded to: {model_dir}")

5. Obtain the upstream vocoder

This repository does not redistribute vocoder.onnx.

Download vocoder.onnx from the official upstream repository:

Supertone/supertonic-3

Place it inside the downloaded model directory:

supertonic-zh/
├── text_encoder_zh.onnx
├── duration_predictor_zh.onnx
├── vector_estimator_zh.onnx
├── unicode_indexer_zh.json
├── voice_zh.json
├── example_infer.py
└── vocoder.onnx

6. Generate speech

cd supertonic-zh

python example_infer.py \
  "今天天气很好，我们一起去公园散步吧。"

The generated audio is saved as:

out.wav

Python example

import subprocess
import sys
from pathlib import Path

model_dir = Path("./supertonic-zh")
script_path = model_dir / "example_infer.py"

required_files = [
    "text_encoder_zh.onnx",
    "duration_predictor_zh.onnx",
    "vector_estimator_zh.onnx",
    "unicode_indexer_zh.json",
    "voice_zh.json",
    "vocoder.onnx",
    "example_infer.py",
]

missing_files = [
    filename
    for filename in required_files
    if not (model_dir / filename).exists()
]

if missing_files:
    raise FileNotFoundError(
        "Missing required files: " + ", ".join(missing_files)
    )

subprocess.run(
    [
        sys.executable,
        str(script_path),
        "欢迎使用 Supertonic 中文语音合成模型。",
    ],
    cwd=model_dir,
    check=True,
)

Included files

File	Description
`text_encoder_zh.onnx`	Mandarin text encoder
`duration_predictor_zh.onnx`	Mandarin duration predictor
`vector_estimator_zh.onnx`	Mandarin flow/vector estimator
`unicode_indexer_zh.json`	Chinese character tokenizer and vocabulary
`voice_zh.json`	Preset Mandarin voice embedding
`example_infer.py`	Minimal ONNX Runtime inference script

The upstream vocoder.onnx file is required but is not included in this repository.

See example_infer.py for the full ~60-line pipeline (tokenize → text encoder → duration → flow-matching loop → vocoder). No PyTorch required.

🎙️ Voice

Ships a single preset voice (voice_zh.json). Custom voice / voice cloning is a separate capability, not part of this release.

⚠️ Limitations

Residual high-frequency artifact — bounded by the frozen upstream vocoder (never fine-tuned); a ceiling, not a bug.
Chinese⇄English code-switching is currently unreliable — embedded English words can be unclear (the Chinese fine-tune had no English data). On the roadmap.
Tone / polyphone / erhua accuracy are model-inherent to the character-level acoustic model.
Single preset voice.

Treat this as a feasibility preview, not a finished product.

🧾 License & attribution

Base model: Supertonic-3, BigScience Open RAIL-M — its use-based restrictions (Attachment A) apply to this derivative and must be passed on to any downstream user.
This build: additionally non-commercial only because of the Baker/CSMSC training data.
Training data: AISHELL-3 (OpenSLR SLR93, Apache-2.0) + Baker/CSMSC (non-commercial).

Built on the publicly released Supertonic-3 model and sample code by Supertone Inc. This is an independent, unofficial extension.

Downloads last month: -