Model
Qwen2-Audio-7B
An audio large model in the Qwen series with 7B parameters, supporting speech understanding and generation.
Timeline (last 90 days)
Nov 17
On the turn-end detection task, Marimba reaches an AUROC of 0.935, while the comparison models (Qwen3-Omni-30B-A3B, Qwen2-Audio-7B, FireRedAudio 10.6B) range between 0.54 and 0.79.
Unverified50%