Audio-Text-to-Text
Transformers
Safetensors
vibevoice_asr
automatic-speech-recognition
ASR
Diarization
Speech-to-Text
Transcription
torchao
Instructions to use Matir/VibeVoice-ASR-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Matir/VibeVoice-ASR-HF with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Matir/VibeVoice-ASR-HF") model = AutoModelForMultimodalLM.from_pretrained("Matir/VibeVoice-ASR-HF") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "do_sample": false, | |
| "eos_token_id": [ | |
| 151643, | |
| 151647 | |
| ], | |
| "max_new_tokens": 16384, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 151655, | |
| "transformers_version": "5.9.0", | |
| "use_cache": true, | |
| "repetition_penalty": 1.1, | |
| "no_repeat_ngram_size": 5, | |
| "cache_implementation": "static" | |
| } | |