| --- |
| license: cc-by-4.0 |
| pretty_name: akouo — speaker diarization (Core ML) |
| viewer: false |
| library_name: whisperkit |
| tags: |
| - speakerkit |
| - pyannote |
| - diarization |
| - speaker-diarization |
| - coreml |
| --- |
| |
| # akouo — speaker diarization (Core ML) |
|
|
| Core ML speaker segmentation and embedding models, used by |
| [akouo for iOS](https://github.com/tinypocket/akouo-ios) to work out who spoke when — entirely on |
| device. |
|
|
| This is a **mirror**, hosted so the app does not depend on a third-party repository at runtime. |
| The weights are unmodified. |
|
|
| ## Provenance |
|
|
| - Converted to Core ML by **Argmax**, from |
| [argmaxinc/speakerkit-coreml](https://huggingface.co/argmaxinc/speakerkit-coreml). |
| - Derived from **pyannote** speaker models. |
| - Runs via SpeakerKit, part of [WhisperKit](https://github.com/argmaxinc/WhisperKit) (MIT). |
|
|
| ## Licence — attribution required |
|
|
| **CC-BY-4.0.** |
|
|
| The upstream pyannote models carry mixed terms: `pyannote/segmentation-3.0` is MIT, while |
| `pyannote/wespeaker-voxceleb-resnet34-LM` and `pyannote/speaker-diarization-community-1` are |
| CC-BY-4.0. Where bundled components differ, the most restrictive governs — so CC-BY-4.0 applies to |
| this repository as a whole. |
|
|
| **If you redistribute these weights or ship them inside an application, you must credit pyannote |
| visibly.** This is a condition of the licence, not a courtesy. |
|
|
| Argmax does not declare a licence on the source repository. The licence stated here is a good-faith |
| reading of what these weights derive from, not a grant by tinypocket. |
|
|
