Qwen3-ASR Technical Report

TL;DR

This paper introduces the Qwen3-ASR family of speech recognition models supporting 52 languages, achieving state-of-the-art performance and efficiency, along with a novel non-autoregressive forced alignment model, all released under open-source license.

Contribution

The paper presents new large-scale multilingual ASR models with state-of-the-art accuracy and a novel NAR forced aligner, enhancing real-world applicability and efficiency.

Findings

Qwen3-ASR-1.7B achieves SOTA open-source ASR performance.

Qwen3-ASR-0.6B offers optimal accuracy-efficiency balance.

Qwen3-ForcedAligner outperforms existing models in speed and versatility.

Abstract

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.