Automatic Speech Recognition
MLX
Safetensors
VibeVoice
mlx-audio
speech-to-text
streaming
speaker-diarization
apple-silicon
quantized
4bit
4-bit precision
Instructions to use mlx-community/VibeVoice-ASR-Streaming-7B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/VibeVoice-ASR-Streaming-7B-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/VibeVoice-ASR-Streaming-7B-4bit --local-dir VibeVoice-ASR-Streaming-7B-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from mlx-community/VibeVoice-ASR-Streaming-7B-4bit: direct link, hf CLI and curl.
- Browser
- Download file 192 Bytes
-
https://huggingface.co/mlx-community/VibeVoice-ASR-Streaming-7B-4bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://mlx-community/VibeVoice-ASR-Streaming-7B-4bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/mlx-community/VibeVoice-ASR-Streaming-7B-4bit/resolve/main/preprocessor_config.json
192 Bytes
| { | |
| "speech_tok_compress_ratio": 3200, | |
| "target_sample_rate": 24000, | |
| "normalize_audio": false, | |
| "chunk_frames": 22, | |
| "lookahead_frames": 4, | |
| "processor_class": "VibeVoiceASRProcessor" | |
| } | |