ttslab/chatterbox-turbo-webgpu
By ttslab · ↓ 132 · ♥ 0 · Updated 2026-03-03
What's in this repo
This page lists the files in ttslab/chatterbox-turbo-webgpu, including conditional_decoder_q4f16.onnx, embed_tokens_q4f16.onnx, language_model_q4f16.onnx and more.
- 4 ONNX models (.onnx files)
- 15 files, including 5 .json, 4 .onnx, 4 .onnx_data, 1 .md
- Last updated 2026-03-03
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/conditional_decoder_q4f16.onnx | — | Download |
| onnx/embed_tokens_q4f16.onnx | — | Download |
| onnx/language_model_q4f16.onnx | — | Download |
| onnx/speech_encoder_q4f16.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
Chatterbox Turbo - WebGPU Compatible
This is a WebGPU-compatible version of ResembleAI/chatterbox-turbo-ONNX.
Changes from Original
The original model contains int64 Cast operations and tensors that WebGPU cannot execute.
This version converts all int64 operations to int32, enabling direct WebGPU inference.
Modifications Made:
- conditional_decoder: 521 Cast nodes inserted (376 Shape/Range ops)
- speech_encoder: 350 Cast nodes inserted (243 Shape/Range ops)
- language_model: 3 Cast nodes inserted
- embed_tokens: 1 Cast node inserted
Usage with Transformers.js
import { AutoModel, AutoProcessor } from '@huggingface/transformers';
const model = await AutoModel.from_pretrained('spacekaren/chatterbox-turbo-webgpu', {
device: 'webgpu',
dtype: 'q4f16',
});
const processor = await AutoProcessor.from_pretrained('spacekaren/chatterbox-turbo-webgpu');
Model Size
- Total: ~539 MB (q4f16 quantization)
- Same architecture as original, just int64→int32 conversion
License
MIT (same as original)
Credits
- Original model: ResembleAI/chatterbox-turbo-ONNX
- Conversion script: local.core/scripts/convert_int64_to_int32.py
Model info
Created: 2026-02-27
Updated: 2026-03-03
View on Hugging FaceFiles (15)
Related models
More from ttslab
No other models by this author.