Instructions to use tinypocket/akouo-whisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use tinypocket/akouo-whisper with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| pretty_name: akouo — Whisper (Core ML) | |
| viewer: false | |
| library_name: whisperkit | |
| tags: | |
| - whisper | |
| - whisperkit | |
| - coreml | |
| - asr | |
| - automatic-speech-recognition | |
| # akouo — Whisper (Core ML) | |
| Core ML builds of OpenAI Whisper, used by [akouo for iOS](https://github.com/tinypocket/akouo-ios) | |
| for fully on-device transcription. | |
| 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/whisperkit-coreml](https://huggingface.co/argmaxinc/whisperkit-coreml). | |
| - Original models: **OpenAI Whisper** — `tiny`, `base`, `small`. | |
| - Runs via [WhisperKit](https://github.com/argmaxinc/WhisperKit) (MIT). | |
| ## Licence | |
| **Apache-2.0**, inherited from the upstream OpenAI Whisper models, each of which is published under | |
| Apache-2.0 on the Hub. Core ML conversion does not alter the terms. | |
| Note that 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. | |