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
Update function signature for `generate_transcription`
#2
by m16b - opened
README.md
CHANGED
|
@@ -43,7 +43,7 @@ from mlx_audio.stt.generate import generate_transcription
|
|
| 43 |
model = load_model("mlx-community/VibeVoice-ASR-4bit")
|
| 44 |
transcription = generate_transcription(
|
| 45 |
model=model,
|
| 46 |
-
|
| 47 |
output_path="path_to_output.txt",
|
| 48 |
format="txt",
|
| 49 |
verbose=True,
|
|
|
|
| 43 |
model = load_model("mlx-community/VibeVoice-ASR-4bit")
|
| 44 |
transcription = generate_transcription(
|
| 45 |
model=model,
|
| 46 |
+
audio="path_to_audio.wav",
|
| 47 |
output_path="path_to_output.txt",
|
| 48 |
format="txt",
|
| 49 |
verbose=True,
|