nb-whisper-tiny (MLX, 4-bit quantized)
MLX conversion of NbAiLab/nb-whisper-tiny for fast inference on Apple Silicon via mlx-whisper.
Converted with mlx-examples/whisper/convert.py at 4-bit quantized precision.
Usage
pip install mlx-whisper
mlx_whisper audio_file.mp3 --model FredrikKarlssonSpeech/nb-whisper-tiny-mlx-4bit
import mlx_whisper
result = mlx_whisper.transcribe("audio_file.mp3", path_or_hf_repo="FredrikKarlssonSpeech/nb-whisper-tiny-mlx-4bit")
print(result["text"])
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
4-bit