Qwen3-ASR技术报告

摘要

本报告推出Qwen3-ASR系列模型，包含两款全能语音识别模型与创新的非自回归语音强制对齐模型。Qwen3-ASR-1.7B和Qwen3-ASR-0.6B作为支持52种语言/方言识别的语音识别模型，依托大规模语音训练数据与基础模型Qwen3-Omni强大的音频理解能力。除开源基准测试外，我们还进行了全面的内部评估——因为语音识别模型在开源基准上的分数差异可能微小，但在实际场景中却存在显著质量差异。实验表明：1.7B版本在开源ASR模型中达到SOTA性能，与最强商用API竞争力相当；0.6B版本则实现了最佳的精度-效率平衡，其平均首字延迟可低至92毫秒，在128并发下仅需1秒即可完成2000秒语音转写。Qwen3-ForcedAligner-0.6B是基于大语言模型的非自回归时间戳预测器，可支持11种语言的文本-语音对齐。时间戳精度实验证明，该模型在三大主流强制对齐工具中表现最优，并在效率与多语言适应性方面更具优势。为加速语音识别与音频理解领域的社区研究，我们已将全系列模型基于Apache 2.0协议开源。

English

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects. Both of them leverage large-scale speech training data and the strong audio understanding ability of their foundation model Qwen3-Omni. We conduct comprehensive internal evaluation besides the open-sourced benchmarks as ASR models might differ little on open-sourced benchmark scores but exhibit significant quality differences in real-world scenarios. The experiments reveal that the 1.7B version achieves SOTA performance among open-sourced ASR models and is competitive with the strongest proprietary APIs while the 0.6B version offers the best accuracy-efficiency trade-off. Qwen3-ASR-0.6B can achieve an average TTFT as low as 92ms and transcribe 2000 seconds speech in 1 second at a concurrency of 128. Qwen3-ForcedAligner-0.6B is an LLM based NAR timestamp predictor that is able to align text-speech pairs in 11 languages. Timestamp accuracy experiments show that the proposed model outperforms the three strongest force alignment models and takes more advantages in efficiency and versatility. To further accelerate the community research of ASR and audio understanding, we release these models under the Apache 2.0 license.

Qwen3-ASR技术报告

Qwen3-ASR Technical Report

摘要

Support