[KongchangAI]
Model

Qwen3-ASR 0.6B

A small speech recognition model in the Qwen series with 0.6B parameters. It can serve as a feature-extraction backbone for downstream speech tasks.

Timeline (last 90 days)

Nov 16

Marimba proposes using a frozen Qwen3-ASR 0.6B feature extractor as the backbone, paired with lightweight task-specific readout layers, to handle multiple speech decision tasks in a unified way.

Unverified50%

All Facts (1)

Source Articles