LightOnOCR-2 🦉 Collection LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 3 days ago • 13
Parakeet Collection NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants. • 12 items • Updated 3 days ago • 51
Step-Audio-R1 Collection Step-Audio-R1 is the first audio language model to successfully unlock test-time compute scaling. • 4 items • Updated 9 days ago • 18
LightOnOCR 🦉 Collection The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR • 8 items • Updated 3 days ago • 15