Qwen-Audio-3.1-ASR-Flash-Next
A large audio language model from the Qwen team that supports audio understanding and autoregressive text generation. It serves as the underlying model for Qwen-Audio-Jev, providing the audio encoding and language modeling capability on which the decision head operates.
Timeline (last 90 days)
Qwen-Audio-Jev is implemented by adding a dedicated Jev decision head on top of Qwen-Audio-3.1-ASR-Flash-Next, turning audio decision-making from 'generate text then parse' into 'directly output the decision'.
Qwen-Audio-Jev achieves approximately a 20-fold inference speedup compared with the original Qwen-Audio-3.1-ASR-Flash-Next.
All Facts (2)
Qwen-Audio-Jev is implemented by adding a dedicated Jev decision head on top of Qwen-Audio-3.1-ASR-Flash-Next, turning audio decision-making from 'generate text then parse' into 'directly output the decision'.
50%UnverifiedQwen-Audio-Jev achieves approximately a 20-fold inference speedup compared with the original Qwen-Audio-3.1-ASR-Flash-Next.
50%