whisperx has 1.1M monthly downloads and 23K GitHub stars. Version 3.8.6 supports Python <3.14,>=3.10, first published in 2024.
It is actively maintained under a permissive license, last released in May 2026.
It is built on top of ctranslate2, faster-whisper and huggingface-hub. It is used by 31 tracked packages, including millet-pipeline, subtitle-engine and easy-whisperx.
GitHub topics include asr, speech and speech-recognition.
Package Insights
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100Weekly Downloads
GitHub Stars
Downloads by OS
Python Versions
Top Countries
Dependencies
- ctranslate2 >=4.5.0
- faster-whisper >=1.2.0
- huggingface-hub <1.0.0
- nltk >=3.9.1
- numpy >=2.1.0
- omegaconf >=2.3.0
- pandas >=2.2.3
- pyannote-audio >=4.0.0
- torch ~=2.8.0
- torchaudio ~=2.8.0
- torchcodec <0.8.0,>=0.6.0
- torchvision ~=0.23.0
- transformers >=4.48.0
- triton >=3.3.0
1 optional dependencies
- pytest[dev]
Used By
- millet-pipeline
- subtitle-engine
- easy-whisperx
- anchor-sub-sync
- whisply
- tecjustica-transcribe
- yta-audio-transcription-whisperx
- subtatix
- whisperx-nemo-pipeline
- sonata-asr
- meetscribe-offline
- citeindex
- ownscribe
- openwillis-transcribe
- demonstrable-whisperx-service
- transcribe-audio
- whisperx-karaoke
- nophi-av
- witticism
- fave-asr
- whisperx-api
- sub-tools
- vtt-synced-voice
- audio-feature-extractor
- psifx
- mynah-stt
- subcap
- audim
- tecjustica-transcribe-cli
- knit2pdf
- speech-mine