microsoft/Phi-4-multimodal-instruct Automatic Speech Recognition • Updated about 5 hours ago • 7.35k • 513
Ultravox v0.5 Collection Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (fine-tuned) backbone. • 3 items • Updated 18 days ago • 6