{"id":21849,"library":"qwen-asr","title":"Qwen-ASR","description":"Qwen-ASR is a Python package for automatic speech recognition (ASR) using the Qwen3 model family. Version 0.0.6 supports real-time and file-based transcription with speaker diarization. Release cadence is irregular; in early development.","status":"active","version":"0.0.6","language":"python","source_language":"en","source_url":"https://github.com/Qwen/Qwen3-ASR","tags":["asr","speech-recognition","qwen","transcription"],"install":[{"cmd":"pip install qwen-asr","lang":"bash","label":"PyPI install"}],"dependencies":[{"reason":"Required for model inference","package":"torch","optional":false},{"reason":"Provides Qwen model classes","package":"transformers","optional":false},{"reason":"Audio file processing","package":"ffmpeg","optional":false}],"imports":[{"note":"Class name is QwenASR, not ASR","wrong":"from qwen_asr import ASR","symbol":"QwenASR","correct":"from qwen_asr import QwenASR"},{"note":"","wrong":"","symbol":"AudioInput","correct":"from qwen_asr import AudioInput"}],"quickstart":{"code":"from qwen_asr import QwenASR\nimport os\n\napi_key = os.environ.get('QWEN_API_KEY', '')\nmodel = QwenASR(api_key=api_key)\ntranscription = model.transcribe('audio.wav')\nprint(transcription)","lang":"python","description":"Initialize QwenASR with an API key and transcribe an audio file."},"warnings":[{"fix":"Always set the environment variable QWEN_API_KEY or pass api_key explicitly.","message":"The QwenASR constructor requires an `api_key` argument; omitting it or passing a wrong value leads to silent fallback to a local model if available, otherwise fails.","severity":"gotcha","affected_versions":"<=0.0.6"},{"fix":"Use `from qwen_asr import ...` instead of `import qwenasr`.","message":"Version 0.0.6 changed the import path from `qwen_asr` (previously it may have been `qwenasr`).","severity":"breaking","affected_versions":"0.0.6"},{"fix":"Remove `return_dict` parameter; use plain call: `model.transcribe('file.wav')`.","message":"The `transcribe()` method's `return_dict` argument is deprecated; output structure changed in 0.0.6.","severity":"deprecated","affected_versions":"0.0.5"}],"env_vars":null,"last_verified":"2026-04-27T00:00:00.000Z","next_check":"2026-07-26T00:00:00.000Z","problems":[{"fix":"Run `pip install qwen-asr==0.0.6`. Verify with `pip list | grep qwen-asr`.","cause":"Installed wrong package name or version mismatch.","error":"ModuleNotFoundError: No module named 'qwen_asr'"},{"fix":"Use `from qwen_asr import QwenASR` (capital Q, capital A).","cause":"Using an outdated import (e.g., `from qwen_asr import ASR`).","error":"AttributeError: module 'qwen_asr' has no attribute 'QwenASR'"},{"fix":"Set environment variable QWEN_API_KEY or pass the key directly: `QwenASR(api_key='your_key')`.","cause":"Missing API key for cloud-based inference.","error":"ValueError: The api_key must be provided"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"install_tag":null,"quickstart_score":null,"quickstart_tag":null}