AI & ML interests
None defined yet.
Recent Activity
View all activity
Multimodal model for better turn-taking
Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (frozen) backbone.
-
fixie-ai/ultravox-v0_6-llama-3_3-70b
Audio-Text-to-Text • 0.7B • Updated • 10.7k • 9 -
fixie-ai/ultravox-v0_6-gemma-3-27b
Audio-Text-to-Text • 0.7B • Updated • 46.3k • 8 -
fixie-ai/ultravox-v0_6-qwen-3-32b
Audio-Text-to-Text • Updated • 5.08k • 12 -
fixie-ai/ultravox-v0_6-llama-3_1-8b
Audio-Text-to-Text • 0.7B • Updated • 63.6k • 6
Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (fine-tuned) backbone.
-
fixie-ai/ultravox-v0_5-llama-3_3-70b
Audio-Text-to-Text • 0.7B • Updated • 33 • 32 -
fixie-ai/ultravox-v0_5-llama-3_1-8b
Audio-Text-to-Text • Updated • 23.1k • 37 -
fixie-ai/ultravox-v0_5-llama-3_2-1b
Audio-Text-to-Text • 0.7B • Updated • 850k • 77 -
fixie-ai/ultravox-v0_5-glm-4_5-355b
Audio-Text-to-Text • 0.7B • Updated • 6 • 3
-
fixie-ai/ultravox-v0_6-llama-3_3-70b
Audio-Text-to-Text • 0.7B • Updated • 10.7k • 9 -
fixie-ai/ultravox-v0_6-gemma-3-27b
Audio-Text-to-Text • 0.7B • Updated • 46.3k • 8 -
fixie-ai/ultravox-v0_6-qwen-3-32b
Audio-Text-to-Text • Updated • 5.08k • 12 -
fixie-ai/ultravox-v0_6-llama-3_1-8b
Audio-Text-to-Text • 0.7B • Updated • 63.6k • 6
Multimodal model for better turn-taking
Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (fine-tuned) backbone.
-
fixie-ai/ultravox-v0_5-llama-3_3-70b
Audio-Text-to-Text • 0.7B • Updated • 33 • 32 -
fixie-ai/ultravox-v0_5-llama-3_1-8b
Audio-Text-to-Text • Updated • 23.1k • 37 -
fixie-ai/ultravox-v0_5-llama-3_2-1b
Audio-Text-to-Text • 0.7B • Updated • 850k • 77 -
fixie-ai/ultravox-v0_5-glm-4_5-355b
Audio-Text-to-Text • 0.7B • Updated • 6 • 3
Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (frozen) backbone.