FluffyBunnies/vibevoice-onnx-v2
By FluffyBunnies · ↓ 14 · ♥ 5 · Updated 2025-12-12
What's in this repo
This page lists the files in FluffyBunnies/vibevoice-onnx-v2, including acoustic_connector_int4.onnx, diffusion_head_int4.onnx, text_lm_int8.onnx and more.
- 5 ONNX models (.onnx files)
- 10 files, including 5 .onnx, 3 .json, 1 .md
- Last updated 2025-12-12
ONNX files
| File | Size | Download |
|---|---|---|
| acoustic_connector_int4.onnx | — | Download |
| diffusion_head_int4.onnx | — | Download |
| text_lm_int8.onnx | — | Download |
| tts_lm_int8.onnx | — | Download |
| vocoder_int4.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
VibeVoice TTS - ONNX for Browser
Microsoft's VibeVoice-Realtime-0.5B converted to ONNX for browser inference.
Architecture
VibeVoice uses a two-LLM architecture with diffusion-based vocoding:
- Text LM (187 MB INT8) - Processes input text to hidden states
- TTS LM (417 MB INT8) - Generates speech latents autoregressively
- Diffusion Head (25 MB INT4) - Denoises latents
- Vocoder (339 MB INT4) - Converts latents to 24kHz audio
- Acoustic Connector (0.5 MB INT4) - Feeds speech back to TTS LM
Total: ~969 MB quantized (down from 3.8 GB)
Files
text_lm_int8.onnx- Text encodertts_lm_int8.onnx- Speech token generatordiffusion_head_int4.onnx- Latent denoiservocoder_int4.onnx- Audio synthesizeracoustic_connector_int4.onnx- Speech feedbacktokenizer.json- Qwen2 tokenizerconfig.json- Model configuration
Usage
See demo.html for browser usage example.
License
Apache 2.0 (same as original VibeVoice model)
Model info
Created: 2025-12-12
Updated: 2025-12-12
View on Hugging FaceFiles (10)
Related models
More from FluffyBunnies
More models
No task type declared.