3 projects
polyvoice
Speaker diarization for Python — who spoke when. Rust + ONNX, no Python runtime overhead. K-means/AHC clustering, overlap detection.
gigastt
On-device Russian speech-to-text (GigaAM v3) — Python bindings (no cloud, no API keys)
phostt
On-device Vietnamese speech recognition — Python bindings for phostt
