AI模型精选

阿里发布Qwen-Audio-3.0-ASR-Flash,强化上下文与领域术语识别

Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our l...

精选理由

语音识别总听错专业词?试试这个新模型,医疗术语召回95.36%,还能自定义热词和输出结构化文本。

AI 摘要

阿里云推出ASR模型Qwen-Audio-3.0-ASR-Flash,主打上下文一致性和领域术语识别。内部测试中,医疗术语召回率达95.36%,工业术语召回率达93.24%。该模型支持自定义热词,并可将语音润色为结构化文本。同步提供流式与文件转写两个版本。

原文 · 阿里通义 Qwen

Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our l...

Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our latest ASR model upgrades: • Context consistency • Domain-term recognition • Custom hotwords • Speech polishing into structured transcripts ⚡️In internal tests: • Medical term recall: 95.36% • Industrial term recall: 93.24% Qwen-Audio-3.0-ASR-Flash-Streaming: alibabacloud.com/help/en/model-… J Qwen-Audio-3.0-ASR-Flash-Filetrans: alibabacloud.com/help/en/model-… F Qwen-Audio-3.0-ASR-Flash: alibabacloud.com/help/en/model-… i 💬 25 🔄 31 ❤️ 423 👀 21145 📊 81 ⚡

阿里发布Qwen-Audio-3.0-ASR-Flash,强化上下文与领域术语识别 · AI 热点