Automatic Speech Recognition
Safetensors
MLX
English
Chinese
mlx-audio
vibevoice_asr
ASR
Transcriptoin
Diarization
Speech-to-Text
speech-to-text
speech
transcription
asr
stt
4-bit precision
Instructions to use mlx-community/VibeVoice-ASR-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/VibeVoice-ASR-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir VibeVoice-ASR-4bit mlx-community/VibeVoice-ASR-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Model type None not supported.
#1
by poyhub - opened
Run Device: Macbook Pro M1 Pro
Run code:
from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription
model = load_model("/VibeVoice-ASR-4bit")
transcription = generate_transcription(
model=model,
audio_path="path_to_audio.wav",
output_path="path_to_output.txt",
format="txt",
verbose=True,
)
print(transcription.text)
ERROR:root:Model type None not supported.