{"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,"search_vec":"'0.0.6':22 'asr':3,6,15,42 'automat':12 'base':30 'cadenc':36 'develop':41 'diariz':34 'earli':40 'famili':20 'file':29 'file-bas':28 'irregular':38 'model':19 'packag':10 'python':9 'qwen':2,5,46 'qwen-asr':1,4 'qwen3':18 'real':25 'real-tim':24 'recognit':14,45 'releas':35 'speaker':33 'speech':13,44 'speech-recognit':43 'support':23 'time':26 'transcript':31,47 'use':16 'version':21","created_at":"2026-04-27T17:02:04.840506+00:00","updated_at":"2026-04-27T17:02:04.840506+00:00","problems":{"verify_error":"/tmp/tmpwckbt0_v/venv/lib/python3.12/site-packages/nagisa/tagger.py:45: SyntaxWarning: invalid escape sequence '\\('\n  single_word_list = [w.replace('(', '\\(').replace(')', '\\)')\n/tmp/tmpwckbt0_v/venv/lib/python3.12/site-packages/nagisa/tagger.py:45: SyntaxWarning: invalid escape sequence '\\)'\n  sing"},"ecosystem":"pypi","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":"0.0.6","cli_name":"","cli_version":null,"type":"library","homepage":null,"github":"https://github.com/Qwen/Qwen3-ASR","docs":null,"changelog":null,"pypi":"https://pypi.org/project/qwen-asr/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["ai-ml"],"base_url":null,"auth_type":null,"provenance":{"verified_status":"install_fail","verified_at":"2026-06-28","last_verified":"2026-06-28","next_check":"2026-07-09","install_tag":null}}