Qwen3-ASR-1.7B

transcriptionapache-2.0

Qwen3-ASR-1.7B is the flagship model of the Qwen3-ASR family: multilingual language identification and speech recognition across 30 languages and 22 Chinese dialects, built on Qwen3-Omni. It reaches state-of-the-art accuracy among open-source ASR models (competitive with strong commercial APIs), with unified streaming/offline inference and segment- and word-level timestamps.

Capabilities

Infrastructure
Streaming
Fine-tuning

Details

Model IDQwen/Qwen3-ASR-1.7B
Provider DeepInfra
Family—
Licenseapache-2.0
Statusactive
Typetranscription
Input modalitiesspeech
Output modalitiestext
Open weightYes
Languages—
Release date
Sourceofficial

Endpoints

audio transcriptionsPOST
https://api.deepinfra.com/v1/openai/audio-transcriptions

API

GET/v1/models/deepinfra/Qwen/Qwen3-ASR-1.7B