Non-real-time speech recognition

import json
import os
import time
from urllib.request import Request, urlopen

api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"
headers = {
    "Authorization": "Bearer " + os.environ["DASHSCOPE_API_KEY"],
    "Content-Type": "application/json",
}
body = {
    "model": "qwen-audio-3.1-asr-flash-filetrans",
    "input": {"file_urls": ["https://g-adoc.alcasset.com/media/maas_docs/sfm-cn/en/audios/6a4b3c2d1e0f9092.wav"]},
    "parameters": {},
}
request = Request(
    api_url + "/services/audio/asr/transcription",
    data=json.dumps(body).encode(),
    headers={**headers, "X-DashScope-Async": "enable"},
)
with urlopen(request) as response:
    task_id = json.load(response)["output"]["task_id"]

while True:
    query = Request(api_url + "/tasks/" + task_id, headers=headers)
    with urlopen(query) as response:
        result = json.load(response)
    status = result["output"]["task_status"]
    if status == "SUCCEEDED":
        break
    if status in ("FAILED", "CANCELED"):
        raise RuntimeError(json.dumps(result, ensure_ascii=False))
    time.sleep(3)

for item in result["output"]["results"]:
    if item["subtask_status"] != "SUCCEEDED":
        raise RuntimeError(json.dumps(item, ensure_ascii=False))
    with urlopen(item["transcription_url"]) as response:
        transcript = json.load(response)
    print(json.dumps(transcript, ensure_ascii=False, indent=2))