Fhrozen/Spark-TTS-0.5B-ONNX
By Fhrozen · ↓ 0 · ♥ 1 · Updated 2025-07-23
What's in this repo
This page lists the files in Fhrozen/Spark-TTS-0.5B-ONNX, including model.onnx, model_bnb4.onnx, model_fp16.onnx and more.
- 9 ONNX models (.onnx files)
- 23 files, including 9 .onnx, 8 .json, 1 .jinja, 1 .txt, 1 .onnx_data, 1 .md
- Last updated 2025-07-23
ONNX files
| File | Size | Download |
|---|---|---|
| LLM/onnx/model.onnx | — | Download |
| LLM/onnx/model_bnb4.onnx | — | Download |
| LLM/onnx/model_fp16.onnx | — | Download |
| LLM/onnx/model_int8.onnx | — | Download |
| LLM/onnx/model_q4.onnx | — | Download |
| LLM/onnx/model_q4f16.onnx | — | Download |
| LLM/onnx/model_quantized.onnx | — | Download |
| LLM/onnx/model_uint8.onnx | — | Download |
| bicodec.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: cc-by-nc-sa-4.0 base_model: SparkAudio/Spark-TTS-0.5B tags:
- ONNX
- ONNXRuntime
- text-to-speech language:
- en
- zh
Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Overview
Spark-TTS is an advanced text-to-speech system that uses the power of large language models (LLM) for highly accurate and natural-sounding voice synthesis. It is designed to be efficient, flexible, and powerful for both research and production use.
https://huggingface.co/SparkAudio/Spark-TTS-0.5B with ONNX weights.
Usage
python test_spark_tts.py --text "Your text to synthesize" --model_dir "/path/to/model"
Model info
Created: 2025-07-23
Updated: 2025-07-23
View on Hugging Face