| library_name: mlx-audio-plus | |
| license: apache-2.0 | |
| base_model: | |
| - openai/whisper-tiny | |
| tags: | |
| - mlx | |
| - whisper | |
| - speech-recognition | |
| - speech-to-text | |
| - stt | |
| pipeline_tag: automatic-speech-recognition | |
| # mlx-community/whisper-tiny-4bit | |
| This model was converted to MLX format from [openai/whisper-tiny](https://github.com/openai/whisper) using [mlx-audio-plus](https://github.com/DePasqualeOrg/mlx-audio-plus) version **0.1.4**. | |
| ## Use with mlx-audio-plus | |
| ```bash | |
| pip install -U mlx-audio-plus | |
| ``` | |
| ### Command line | |
| ```bash | |
| mlx_audio.stt --model mlx-community/whisper-tiny-4bit --audio audio.mp3 | |
| ``` | |
| ### Python | |
| ```python | |
| from mlx_audio.stt import transcribe | |
| result = transcribe( | |
| audio="audio.mp3", | |
| model="mlx-community/whisper-tiny-4bit", | |
| ) | |
| print(result["text"]) | |
| ``` | |