Automatic Speech Recognition
Transformers
Safetensors
VibeVoice
ASR
Transcriptoin
Diarization
Speech-to-Text
8-bit precision
bitsandbytes
Instructions to use Dubedo/VibeVoice-ASR-AutoQ-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Dubedo/VibeVoice-ASR-AutoQ-INT8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Dubedo/VibeVoice-ASR-AutoQ-INT8")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, VibeVoiceForASRTraining processor = AutoProcessor.from_pretrained("Dubedo/VibeVoice-ASR-AutoQ-INT8") model = VibeVoiceForASRTraining.from_pretrained("Dubedo/VibeVoice-ASR-AutoQ-INT8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download .gitattributes from Dubedo/VibeVoice-ASR-AutoQ-INT8: direct link, hf CLI and curl.
- Browser
- Download file 199 Bytes
-
https://huggingface.co/Dubedo/VibeVoice-ASR-AutoQ-INT8/resolve/main/.gitattributes
- Command line
-
hf download hf://Dubedo/VibeVoice-ASR-AutoQ-INT8/.gitattributes
-
curl -L -o .gitattributes https://huggingface.co/Dubedo/VibeVoice-ASR-AutoQ-INT8/resolve/main/.gitattributes
199 Bytes
| *.safetensors filter=lfs diff=lfs merge=lfs -text | |
| figures/VibeVoice_ASR_archi.png filter=lfs diff=lfs merge=lfs -text | |
| figures/language_distribution_horizontal.png filter=lfs diff=lfs merge=lfs -text | |