# Qwen3 Family Expands into Speech Recognition

> Alibaba's Qwen team has released a new 1.7-billion-parameter model designed specifically for automatic speech recognition.

Published by The Open Weights on Jan 28, 2026. Canonical: https://theopenweights.com/news/qwen3-asr-1-7b-r2hk

## Key facts

- Company: Qwen · Alibaba
- Model: Qwen3-ASR-1.7B
- Version: 3-ASR-1.7B
- Category: Speech → Text
- Modalities: Speech → Text
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 1.7B
- Architecture: Qwen3ASRForConditionalGeneration
- Precision: BF16
- Weights size: 4.7 GB
- Languages: 30 languages, 22 dialects
- Significance: notable
- Published: 2026-01-28
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/Qwen/Qwen3-ASR-1.7B
- Canonical URL: https://theopenweights.com/news/qwen3-asr-1-7b-r2hk

The Qwen team at Alibaba has released Qwen3-ASR-1.7B, extending its new generation of models into the domain of audio processing. This 1.7-billion-parameter model is designed for automatic speech recognition (ASR), also known as speech-to-text, and is now available on the [Hugging Face Hub](https://huggingface.co/Qwen/Qwen3-ASR-1.7B).

Unlike general-purpose language models, Qwen3-ASR is a specialized tool focused on a single task: accurately transcribing spoken language into written text. This makes it a foundational component for a wide range of applications, from creating meeting transcripts and video subtitles to enabling voice-activated user interfaces and accessibility tools.

The release provides another strong open-source option in a field largely defined by models like OpenAI's Whisper. With its Apache 2.0 license, Qwen3-ASR-1.7B offers a permissively licensed alternative for developers and businesses to build upon without restrictive terms. Its relatively moderate size suggests a balance between performance and computational efficiency, making it potentially suitable for a variety of hardware environments.

## Get the model

- [Hugging Face](https://huggingface.co/Qwen/Qwen3-ASR-1.7B)

## Sources

- [Qwen/Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B) — Hugging Face, Jan 28, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Qwen3 Family Expands into Speech Recognition", The Open Weights, Jan 28, 2026, https://theopenweights.com/news/qwen3-asr-1-7b-r2hk