{"library":"whisperx","type":"library","category":null,"description":"WhisperX is a Python library that provides time-accurate Automatic Speech Recognition (ASR) using OpenAI's Whisper model, enhanced with speaker diarization. It supports a range of models, languages, and device configurations (CPU/GPU) to offer high-quality transcription with precise timestamps and speaker identification. The current version is 3.8.5, and it maintains an active release cadence with frequent updates.","language":"python","status":"active","version":"3.8.5","tags":["speech-to-text","audio-processing","ai","whisper","diarization","asr"],"last_verified":"Fri May 22","install":[{"cmd":"pip install whisperx torch==2.3.0 torchvision==0.18.0 torchaudio==2.3.0 --index-url https://download.pytorch.org/whl/cu121","imports":["import whisperx\nmodel = whisperx.load_model(...)","import whisperx\naudio = whisperx.load_audio(...)","from whisperx import DiarizationPipeline\ndiarize_model = DiarizationPipeline(...)","import whisperx\nmodel_a, metadata = whisperx.load_align_model(...)","import whisperx\nresult = whisperx.assign_speakers(...)"]},{"cmd":"pip install whisperx torch==2.3.0 torchvision==0.18.0 torchaudio==2.3.0","imports":[]},{"cmd":"pip install requests","imports":[]}],"homepage":null,"github":"https://github.com/m-bain/whisperx","docs":null,"changelog":null,"pypi":"https://pypi.org/project/whisperx/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":33,"avg_install_s":2.3,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/whisperx/compatibility"}}