bash
Download through ModelScope (recommended for users in Mainland China)
pip install -U modelscope
modelscope download --model Qwen/Qwen3-ASR-1.7B  --local_dir ./Qwen3-ASR-1.7B
modelscope download --model Qwen/Qwen3-ASR-0.6B --local_dir ./Qwen3-ASR-0.6B
modelscope download --model Qwen/Qwen3-ForcedAligner-0.6B --local_dir ./Qwen3-ForcedAligner-0.6B
Download through Hugging Face
pip install -U "huggingface_hub[cli]"
huggingface-cli download Qwen/Qwen3-ASR-1.7B --local-dir ./Qwen3-ASR-1.7B
huggingface-cli download Qwen/Qwen3-ASR-0.6B --local-dir ./Qwen3-ASR-0.6B
huggingface-cli download Qwen/Qwen3-ForcedAligner-0.6B --local-dir ./Qwen3-ForcedAligner-0.6B

bash
conda create -n qwen3-asr python=3.12 -y
conda activate qwen3-asr

bash
pip install -U qwen-asr

bash
pip install -U qwen-asr[vllm]

bash
git clone https://github.com/QwenLM/Qwen3-ASR.git
cd Qwen3-ASR
pip install -e .
support vLLM backend
pip install -e ".[vllm]"

bash
pip install -U flash-attn --no-build-isolation

bash
MAX_JOBS=4 pip install -U flash-attn --no-build-isolation

python
import torch
from qwen_asr import Qwen3ASRModel

model = Qwen3ASRModel.from_pretrained(
    "Qwen/Qwen3-ASR-1.7B",
    dtype=torch.bfloat16,
    device_map="cuda:0",
    
attn_implementation="flash_attention_2",
    max_inference_batch_size=32, 
Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
    max_new_tokens=256, 
Maximum number of tokens to generate. Set a larger value for long audio input.
)

results = model.transcribe(
    audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
    language=None, 
set "English" to force the language
)

print(results[0].language)
print(results[0].text)

python
import torch
from qwen_asr import Qwen3ASRModel

model = Qwen3ASRModel.from_pretrained(
    "Qwen/Qwen3-ASR-1.7B",
    dtype=torch.bfloat16,
    device_map="cuda:0",
    
attn_implementation="flash_attention_2",
    max_inference_batch_size=32, 
Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
    max_new_tokens=256, 
Maximum number of tokens to generate. Set a larger value for long audio input.
    forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
    forced_aligner_kwargs=dict(
        dtype=torch.bfloat16,
        device_map="cuda:0",
        
attn_implementation="flash_attention_2",
    ),
)

results = model.transcribe(
    audio=[
      "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
      "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
    ],
    language=["Chinese", "English"], 
can also be set to None for automatic language detection
    return_time_stamps=True,
)

for r in results:
    print(r.language, r.text, r.time_stamps[0])

python
import torch
from qwen_asr import Qwen3ASRModel

if __name__ == '__main__':
    model = Qwen3ASRModel.LLM(
        model="Qwen/Qwen3-ASR-1.7B",
        gpu_memory_utilization=0.7,
        max_inference_batch_size=128, 
Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
        max_new_tokens=4096, 
Maximum number of tokens to generate. Set a larger value for long audio input.
        forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
        forced_aligner_kwargs=dict(
            dtype=torch.bfloat16,
            device_map="cuda:0",
            
attn_implementation="flash_attention_2",
        ),
    )

    results = model.transcribe(
        audio=[
        "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
        "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
        ],
        language=["Chinese", "English"], 
can also be set to None for automatic language detection
        return_time_stamps=True,
    )

    for r in results:
        print(r.language, r.text, r.time_stamps[0])

bash
qwen-asr-serve Qwen/Qwen3-ASR-1.7B --gpu-memory-utilization 0.8 --host 0.0.0.0 --port 8000

python
import requests

url = "http://localhost:8000/v1/chat/completions"
headers = {"Content-Type": "application/json"}

data = {
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio_url",
                    "audio_url": {
                        "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
                    },
                }
            ],
        }
    ]
}

response = requests.post(url, headers=headers, json=data, timeout=300)
response.raise_for_status()
content = response.json()['choices'][0]['message']['content']
print(content)

parse ASR output if you want
from qwen_asr import parse_asr_output
language, text = parse_asr_output(content)
print(language)
print(text)

python
import torch
from qwen_asr import Qwen3ForcedAligner

model = Qwen3ForcedAligner.from_pretrained(
    "Qwen/Qwen3-ForcedAligner-0.6B",
    dtype=torch.bfloat16,
    device_map="cuda:0",
    
attn_implementation="flash_attention_2",
)

results = model.align(
    audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
    text="甚至出现交易几乎停滞的情况。",
    language="Chinese",
)

print(results[0])
print(results[0][0].text, results[0][0].start_time, results[0][0].end_time)

bash
qwen-asr-demo --help

bash
Transformers backend
qwen-asr-demo \
  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
  --backend transformers \
  --cuda-visible-devices 0 \
  --ip 0.0.0.0 --port 8000

Transformers backend + Forced Aligner (enable timestamps)
qwen-asr-demo \
  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
  --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B \
  --backend transformers \
  --cuda-visible-devices 0 \
  --backend-kwargs '{"device_map":"cuda:0","dtype":"bfloat16","max_inference_batch_size":8,"max_new_tokens":256}' \
  --aligner-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}' \
  --ip 0.0.0.0 --port 8000

vLLM backend + Forced Aligner (enable timestamps)
qwen-asr-demo \
  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
  --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B \
  --backend vllm \
  --cuda-visible-devices 0 \
  --backend-kwargs '{"gpu_memory_utilization":0.7,"max_inference_batch_size":8,"max_new_tokens":2048}' \
  --aligner-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}' \
  --ip 0.0.0.0 --port 8000

bash
Example: override transformers init args without flash attention
--backend-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}'

Example: override vLLM init args with 65% GPU memory
--backend-kwargs '{"gpu_memory_utilization":0.65}'

bash
Use GPU 0
--cuda-visible-devices 0

Use GPU 1
--cuda-visible-devices 1

bash
No forced aligner
qwen-asr-demo --asr-checkpoint Qwen/Qwen3-ASR-1.7B

With forced aligner
qwen-asr-demo \
  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
  --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B

bash
openssl req -x509 -newkey rsa:2048 \
  -keyout key.pem -out cert.pem \
  -days 365 -nodes \
  -subj "/CN=localhost"

bash
qwen-asr-demo \
  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
  --backend transformers \
  --cuda-visible-devices 0 \
  --ip 0.0.0.0 --port 8000 \
  --ssl-certfile cert.pem \
  --ssl-keyfile key.pem \
  --no-ssl-verify

bash
qwen-asr-demo-streaming \
  --asr-model-path Qwen/Qwen3-ASR-1.7B \
  --host 0.0.0.0 \
  --port 8000 \
  --gpu-memory-utilization 0.9

bash
uv venv
source .venv/bin/activate
uv pip install -U vllm --pre \
    --extra-index-url https://wheels.vllm.ai/nightly/cu129 \
    --extra-index-url https://download.pytorch.org/whl/cu129 \
    --index-strategy unsafe-best-match
uv pip install "vllm[audio]" 
For additional audio dependencies

bash
vllm serve Qwen/Qwen3-ASR-1.7B

python
import base64
import httpx
from openai import OpenAI

Initialize client
client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY"
)

Create multimodal chat completion request
response = client.chat.completions.create(
    model="Qwen/Qwen3-ASR-1.7B",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "audio_url",
                    "audio_url": {
                        {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"}
                    }
                }
            ]
        }
    ],
)

print(response.choices[0].message.content)

python
import httpx
from openai import OpenAI

Initialize client
client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY"
)
audio_url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
audio_file = httpx.get(audio_url).content

transcription = client.audio.transcriptions.create(
    model="Qwen/Qwen3-ASR-1.7B",
    file=audio_file,
)

print(transcription.text)

bash
curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "messages": [
    {"role": "user", "content": [
        {"type": "audio_url", "audio_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"}}
    ]}
    ]
    }'

python
from vllm import LLM, SamplingParams
from vllm.assets.audio import AudioAsset
import base64
import requests

Initialize the LLM
llm = LLM(
    model="Qwen/Qwen3-ASR-1.7B"
)

Load audio
audio_asset = AudioAsset("winning_call")

Create conversation with audio content
conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio_url",
                "audio_url": {"url": audio_asset.url}
            }
        ]
    }
]

sampling_params = SamplingParams(temperature=0.01, max_tokens=256)

Run inference using .chat()
outputs = llm.chat(conversation, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)

bash
LOCAL_WORKDIR=/path/to/your/workspace
HOST_PORT=8000
CONTAINER_PORT=80
docker run --gpus all --name qwen3-asr \
    -v /var/run/docker.sock:/var/run/docker.sock -p $HOST_PORT:$CONTAINER_PORT \
    --mount type=bind,source=$LOCAL_WORKDIR,target=/data/shared/Qwen3-ASR \
    --shm-size=4gb \
    -it qwenllm/qwen3-asr:latest

bash
docker start qwen3-asr
docker exec -it qwen3-asr bash

bash
docker rm -f qwen3-asr

BibTeX
@article{Qwen3-ASR,
  title={Qwen3-ASR Technical Report},
  author={Xian Shi, Xiong Wang, Zhifang Guo, Yongqi Wang, Pei Zhang, Xinyu Zhang, Zishan Guo, Hongkun Hao, Yu Xi, Baosong Yang, Jin Xu, Jingren Zhou, Junyang Lin},
  journal={arXiv preprint arXiv:2601.21337},
  year={2026}
}