ONNX Model Zoo

jb2n95/model-mirror-tonic

By jb2n95 · ↓ 0 · ♥ 1 · Updated 2026-02-04

What's in this repo

This page lists the files in jb2n95/model-mirror-tonic, including duration_predictor.onnx, text_encoder.onnx, vector_estimator.onnx and more.

  • 8 ONNX models (.onnx files)
  • 35 files, including 24 .json, 8 .onnx, 1 .md
  • Last updated 2026-02-04

ONNX files

File Size Download
fp16/onnx/duration_predictor.onnx — Download
fp16/onnx/text_encoder.onnx — Download
fp16/onnx/vector_estimator.onnx — Download
fp16/onnx/vocoder.onnx — Download
fp32/onnx/duration_predictor.onnx — Download
fp32/onnx/text_encoder.onnx — Download
fp32/onnx/vector_estimator.onnx — Download
fp32/onnx/vocoder.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README


license: openrail

Supertonic-2 TTS Model Mirror

Mirror of Supertone/supertonic-2 with additional float16 quantized version.

Model Versions

Version Path Total Size Description
fp32 (Original) fp32/ ~251MB Original float32 precision
fp16 (Quantized) fp16/ ~126MB Float16 quantized (~50% smaller)

Directory Structure

├── fp32/                    # Original float32 version
│   ├── onnx/
│   │   ├── duration_predictor.onnx (1.5MB)
│   │   ├── text_encoder.onnx (26MB)
│   │   ├── vector_estimator.onnx (126MB)
│   │   ├── vocoder.onnx (97MB)
│   │   ├── tts.json
│   │   └── unicode_indexer.json
│   └── voice_styles/
│       ├── F1.json ~ F5.json (Female voices)
│       └── M1.json ~ M5.json (Male voices)
│
└── fp16/                    # Float16 quantized version
    ├── onnx/
    │   ├── duration_predictor.onnx (0.8MB)
    │   ├── text_encoder.onnx (13MB)
    │   ├── vector_estimator.onnx (63MB)
    │   ├── vocoder.onnx (48MB)
    │   ├── tts.json
    │   └── unicode_indexer.json
    └── voice_styles/
        └── (same as fp32)

Usage

Clone specific version

# Clone entire repository
git clone https://huggingface.co/jb2n95/model-mirror-tonic

# Or use git sparse-checkout for specific version
git clone --filter=blob:none --sparse https://huggingface.co/jb2n95/model-mirror-tonic
cd model-mirror-tonic
git sparse-checkout set fp16  # or fp32

In Docker

# For fp32 (original)
RUN git clone --depth 1 https://huggingface.co/jb2n95/model-mirror-tonic && \
    mv model-mirror-tonic/fp32/* public/assets/ && \
    rm -rf model-mirror-tonic

# For fp16 (smaller, faster download)
RUN git clone --depth 1 https://huggingface.co/jb2n95/model-mirror-tonic && \
    mv model-mirror-tonic/fp16/* public/assets/ && \
    rm -rf model-mirror-tonic

Changes from Original

  • fp16 version: Converted from float32 to float16 using onnxconverter-common
  • No other modifications to model architecture or weights

License

This model is distributed under the OpenRAIL-M License, same as the original.

Attribution

Supported Languages

  • Korean (ko)
  • English (en)
  • Spanish (es)
  • Portuguese (pt)
  • French (fr)

Model info

onnx license:openrail region:us
↓ 0 ♥ 1

Created: 2026-02-04

Updated: 2026-02-04

View on Hugging Face

Files (35)

.gitattributes
LICENSE
README.md
fp16/onnx/duration_predictor.onnx ONNX
fp16/onnx/text_encoder.onnx ONNX
fp16/onnx/tts.json
fp16/onnx/unicode_indexer.json
fp16/onnx/vector_estimator.onnx ONNX
fp16/onnx/vocoder.onnx ONNX
fp16/voice_styles/F1.json
fp16/voice_styles/F2.json
fp16/voice_styles/F3.json
fp16/voice_styles/F4.json
fp16/voice_styles/F5.json
fp16/voice_styles/M1.json
fp16/voice_styles/M2.json
fp16/voice_styles/M3.json
fp16/voice_styles/M4.json
fp16/voice_styles/M5.json
fp32/onnx/duration_predictor.onnx ONNX
fp32/onnx/text_encoder.onnx ONNX
fp32/onnx/tts.json
fp32/onnx/unicode_indexer.json
fp32/onnx/vector_estimator.onnx ONNX
fp32/onnx/vocoder.onnx ONNX
fp32/voice_styles/F1.json
fp32/voice_styles/F2.json
fp32/voice_styles/F3.json
fp32/voice_styles/F4.json
fp32/voice_styles/F5.json
fp32/voice_styles/M1.json
fp32/voice_styles/M2.json
fp32/voice_styles/M3.json
fp32/voice_styles/M4.json
fp32/voice_styles/M5.json

Related models