# Qwen3-ASR Technical Report

arXiv: https://arxiv.org/abs/2601.21337 · HTML: https://mlsanity.com/paper/2601.21337/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 12 of 12)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model](https://mlsanity.com/paper/2301.12343/) (2023)
- [Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods](https://mlsanity.com/paper/2509.13785/) (2025)
- [WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation](https://mlsanity.com/paper/2509.03959/) (2025)
- [LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech](https://mlsanity.com/paper/2601.18220/) (2026)
- [WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing](https://mlsanity.com/paper/2509.18004/) (2025)

## Built on by (most cited first, 30 of 118)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks](https://mlsanity.com/paper/2607.05369/) (2026)
- [MOSS-Audio Technical Report](https://mlsanity.com/paper/2606.01802/) (2026)
- [PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory](https://mlsanity.com/paper/2604.08000/) (2026)
- [Raon-Speech Technical Report](https://mlsanity.com/paper/2605.23912/) (2026)
- [Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2603.11123/) (2026)
- [Dynin-Omni: Omnimodal Unified Large Diffusion Language Model](https://mlsanity.com/paper/2604.00007/) (2026)
- [Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation](https://mlsanity.com/paper/2605.19833/) (2026)
- [Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization](https://mlsanity.com/paper/2604.06138/) (2026)
- [Audio Interaction Model](https://mlsanity.com/paper/2606.05121/) (2026)
- [Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding](https://mlsanity.com/paper/2603.06193/) (2026)
- [ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models](https://mlsanity.com/paper/2604.10065/) (2026)
- [X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction](https://mlsanity.com/paper/2608.10878/) (2026)
- [Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling](https://mlsanity.com/paper/2604.23586/) (2026)
- [Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation](https://mlsanity.com/paper/2605.29430/) (2026)
- [MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering](https://mlsanity.com/paper/2606.05917/) (2026)
- [VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction](https://mlsanity.com/paper/2608.26005/) (2026)
- [Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR](https://mlsanity.com/paper/2603.05354/) (2026)
- [TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild](https://mlsanity.com/paper/2603.21478/) (2026)
- [Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment](https://mlsanity.com/paper/2604.06191/) (2026)
- [Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs](https://mlsanity.com/paper/2604.08003/) (2026)
- [Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition](https://mlsanity.com/paper/2604.09121/) (2026)
- [NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR](https://mlsanity.com/paper/2604.18105/) (2026)
- [2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA](https://mlsanity.com/paper/2604.23935/) (2026)
- [Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding](https://mlsanity.com/paper/2604.26031/) (2026)
- [When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition](https://mlsanity.com/paper/2605.02782/) (2026)
- [Dolphin-CN-Dialect: Where Chinese Dialects Matter](https://mlsanity.com/paper/2605.08961/) (2026)
- [FormalASR: End-to-End Spoken Chinese to Formal Text](https://mlsanity.com/paper/2605.19266/) (2026)
- [LaSR: Context-Aware Speech Recognition via Latent Reasoning](https://mlsanity.com/paper/2606.00507/) (2026)
- [FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition](https://mlsanity.com/paper/2606.06211/) (2026)

## Abstract (arXiv)

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.