Qwen3-ASR 1.7B

State-of-the-art multilingual speech recognition across 52 languages & dialects

MultilingualApache-2.0
Desktop app Open the Models screen and click install.
CLI
$ openasr pull qwen3-asr-1.7b:q8
Download .oasr

Overview

Qwen3-ASR-1.7B is a multilingual automatic speech recognition model (~2B parameters, ~1.7B active, BF16) from Alibaba's Qwen3-ASR family that transcribes speech while identifying the spoken language across 30 languages, 22 Chinese dialects, and a range of regional English accents — and it holds up on hard audio including singing voice and songs over background music. A single unified checkpoint serves both offline and real-time streaming transcription, with word-level timestamps available via the companion Qwen3-ForcedAligner-0.6B; the Qwen team reports state-of-the-art quality among open-source ASR models and accuracy competitive with commercial APIs. This OpenASR repo repackages the original Qwen/Qwen3-ASR-1.7B weights as .oasr packs that run natively in the OpenASR runtime with no Python at inference time. For most users the q8_0 build is the recommended default — near-reference accuracy at roughly half the footprint — while q4_k suits tight-memory deployments and fp16 is reserved for verification or maximum fidelity.

Highlights

  • 🏆 SOTA among open-source ASR — competitive with the strongest proprietary commercial APIs
  • 🌍 52 languages & dialects — 30 languages plus 22 Chinese dialects, with spoken-language identification
  • 🎧 Robust on hard audio — clean speech, singing voice, and songs over background music
  • 🦀 Native in OpenASR.oasr packs run with no Python at inference, engineered for peak performance on CPU & GPU

Tags

Pull stringSizeQuantJFK ΔWER
qwen3-asr-1.7b:fp16 4.4 GB fp16 0%
qwen3-asr-1.7b:q8default 2.3 GB q8_0 0%
qwen3-asr-1.7b:q4 1.2 GB q4_k 0%

Usage

These are CLI / local-server examples. The desktop app runs this model without typing a command — see the desktop install path above.

bash · transcribe a file
$ openasr pull qwen3-asr-1.7b:q8
↓ qwen3-asr-1.7b.oasr  2.3 GB  ✓ verified sha256
$ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/qwen3-asr-1.7b/q8_0/qwen3-asr-1.7b-q8_0.oasr
✓ local transcript · 0 bytes sent
bash · serve a local API
$ openasr serve --backend native --model-pack ~/.openasr/models/qwen3-asr-1.7b/q8_0/qwen3-asr-1.7b-q8_0.oasr --addr 127.0.0.1:8080
▶ http://127.0.0.1:8080 · model=qwen3-asr-1.7b · 0 bytes will leave this host
python · client.py
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local")
audio = open("meeting.wav", "rb")
text = client.audio.transcriptions.create(model="qwen3-asr-1.7b", file=audio)

Other models