Audio-Text-to-Text
Transformers
Safetensors
vibevoice_asr
automatic-speech-recognition
ASR
Diarization
Speech-to-Text
Transcription
Instructions to use nivedithahn96/VibeVoice-ASR-HF-Fork with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nivedithahn96/VibeVoice-ASR-HF-Fork with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("nivedithahn96/VibeVoice-ASR-HF-Fork") model = AutoModelForMultimodalLM.from_pretrained("nivedithahn96/VibeVoice-ASR-HF-Fork", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| FROM pytorch/pytorch:2.6.0-cuda12.4-cudnn9-runtime | |
| RUN pip install --no-cache-dir \ | |
| "transformers>=5.3.0" \ | |
| accelerate \ | |
| soundfile \ | |
| fastapi \ | |
| "uvicorn[standard]" \ | |
| huggingface_hub | |
| COPY handler.py /app/handler.py | |
| COPY serve.py /app/serve.py | |
| WORKDIR /app | |
| EXPOSE 5000 | |
| CMD ["uvicorn", "serve:app", "--host", "0.0.0.0", "--port", "5000"] | |