pipecat-ai/smart-turn-v3
By pipecat-ai · ↓ 0 · ♥ 130 · Updated 2026-01-07
What's in this repo
This page lists the files in pipecat-ai/smart-turn-v3, including smart-turn-v3.0.onnx, smart-turn-v3.1-cpu.onnx, smart-turn-v3.1-gpu.onnx and more.
- 5 ONNX models (.onnx files)
- 12 files, including 6 .md, 5 .onnx
- Repository size ~86.8 MB
- Last updated 2026-01-07
ONNX files
| File | Size | Download |
|---|---|---|
| smart-turn-v3.0.onnx | 8.4 MB | Download |
| smart-turn-v3.1-cpu.onnx | 8.3 MB | Download |
| smart-turn-v3.1-gpu.onnx | 30.9 MB | Download |
| smart-turn-v3.2-cpu.onnx | 8.3 MB | Download |
| smart-turn-v3.2-gpu.onnx | 30.9 MB | 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
Smart Turn v3.x
Smart Turn is an open‑source semantic Voice Activity Detection (VAD) model that tells you whether a speaker has finished their turn by analysing the raw waveform, not the transcript.
Links
- Blog post: Smart Turn v3
- GitHub repo with training and inference code, and more information
- Datasets
Model architecture
- Backbone: Whisper Tiny encoder
- Head: shallow linear classifier
- Params: 8M
- Checkpoint: 8 MB ONNX (int8 quantized), 32MB ONNX (unquantized)
How to use
Please see the blog post and GitHub repo for more information on using the model, either standalone or with Pipecat.
Thanks
Thank you to the following organisations for contributing audio datasets:
Model info
Created: 2025-09-11
Updated: 2026-01-07
View on Hugging FaceFiles (12)
Related models
More from pipecat-ai
No other models by this author.