polyvoice 0.6.6

Speaker diarization for Rust — who spoke when. ONNX-powered: Silero VAD, WeSpeaker embeddings, Pyannote segmentation, K-means/AHC clustering, overlap detection.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14

# TODO — src/features

## Current

## Next

- [ ] Add property test: FbankExtractor output dimension matches config.
- [ ] Benchmark extraction speed vs torchaudio reference.

## Known Gaps

## Deferred

- [ ] Add support for 8kHz and 48kHz optimized configs.