Audio-Text-to-Text
Transformers
Safetensors
English
qwen3_omni_moe
text-to-audio
speech
speaker-attribution
multi-party
audio-language-model
Instructions to use PleasedPenguin/A2R-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PleasedPenguin/A2R-30B-A3B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("PleasedPenguin/A2R-30B-A3B") model = AutoModelForMultimodalLM.from_pretrained("PleasedPenguin/A2R-30B-A3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- df93d528ca78938fb5b588dcbd88d2e998b5d003a8f140e9a041280ad118a92c
- Size of remote file:
- 11.4 MB
- SHA256:
- a7d41145c408f3062e824f965be1c29854cd809e111cdf8170aa8b0bcd5d1fab
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.