Alibaba’s Qwen Team Releases Qwen-Audio-3.0-ASR-Flash, an ASR Model Achieving 95.36% Medical Term Recall
English summary
Alibaba’s Qwen team announced Qwen-Audio-3.0-ASR-Flash, a new automatic speech recognition model with three variants: Streaming, Filetrans, and the base Flash. The model introduces context consistency, domain-term recognition, custom hotwords, and speech polishing into structured transcripts. Internal tests show a medical term recall of 95.36% and an industrial term recall of 93.24%.
Chinese summary
阿里通义千问团队发布Qwen-Audio-3.0-ASR-Flash语音识别模型，包含Streaming、Filetrans和基础版三种变体。新模型支持上下文一致性、领域词识别、自定义热词以及将语音润色为结构化文本。内部测试显示医疗术语召回率95.36%，工业术语召回率93.24%。
Key points
Alibaba’s Qwen team released Qwen-Audio-3.0-ASR-Flash with three variants: Streaming, Filetrans, and Flash.
阿里通义千问团队发布了Qwen-Audio-3.0-ASR-Flash，提供Streaming、Filetrans和Flash三种变体。
The model supports context consistency, domain-term recognition, custom hotwords, and speech polishing into structured transcripts.
模型支持上下文一致性、领域词识别、自定义热词和语音润色为结构化文本等功能。
Internal benchmarks report 95.36% medical term recall and 93.24% industrial term recall.
内部测试显示医疗术语召回率95.36%，工业术语召回率93.24%。