SonarScribe — Permissive License Models
This repository contains ASR and audio processing model files used by SonarScribe for offline speech recognition and diarization.
Models
| Model | Folder | License | Source |
|---|---|---|---|
| Zipformer ZH | zipformer-zh/ |
Apache 2.0 | k2-fsa/sherpa-onnx |
| Zipformer KO | zipformer-ko/ |
Apache 2.0 | k2-fsa/sherpa-onnx |
| Zipformer RU | zipformer-ru/ |
Apache 2.0 | k2-fsa/sherpa-onnx |
| Zipformer Multi | zipformer-multi/ |
Apache 2.0 | k2-fsa/sherpa-onnx |
| Whisper tiny (LangId) | whisper-tiny/ |
MIT | OpenAI Whisper |
| Silero VAD | silero-vad/ |
MIT | snakers4/silero-vad |
| Pyannote Segmentation | pyannote-seg/ |
MIT | pyannote/pyannote-audio |
| CamPlus Speaker | camplus/ |
Apache 2.0 | alibaba-damo-academy/3D-Speaker |
License
Models in this repository are distributed under their original licenses (Apache 2.0 or MIT). See each model folder for specific license information.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support