Downloads · 30 days
16
11% of all-time downloads
FredrikKarlssonSpeech/roest-v3-whisper-1.5b-mlx-4bit
roest-v3-whisper-1.5b-mlx-4bit is a automatic speech recognition model from FredrikKarlssonSpeech. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as openrail.
MLX conversion of CoRal-project/roest-v3-whisper-1.5b for fast inference on Apple Silicon via mlx-whisper.
Downloads · 30 days
16
11% of all-time downloads
All-time downloads
152
Public
Repo size
878 MB
Likes
0
Public
Click a slice to open those files.
.safetensors878 MB · 100%
From the Hugging Face model README
MLX conversion of CoRal-project/roest-v3-whisper-1.5b for fast inference on Apple Silicon via mlx-whisper.
Converted with mlx-examples/whisper/convert.py at 4-bit quantized precision.
pip install mlx-whisper
mlx_whisper audio_file.mp3 --model FredrikKarlssonSpeech/roest-v3-whisper-1.5b-mlx-4bit
import mlx_whisper
result = mlx_whisper.transcribe("audio_file.mp3", path_or_hf_repo="FredrikKarlssonSpeech/roest-v3-whisper-1.5b-mlx-4bit")
print(result["text"])