microsoft/Phi-4-multimodal-instruct Automatic Speech Recognition β’ Updated 13 days ago β’ 618k β’ 1.31k
Breeze 2 Family Collection Llama-Breeze2 is a multi-modal language model family specifically intended for Traditional Chinese use. BreezyVoice is a Taiwan Mandarin TTS β’ 6 items β’ Updated Feb 26 β’ 18
SmolVLM 256M & 500M Collection Collection for models & demos for even smoller SmolVLM release β’ 12 items β’ Updated Feb 20 β’ 74