whisperX and whisperVideo
WhisperX provides the core diarization and word-level timestamp functionality that WhisperVideo builds upon to attribute speech segments to speakers in video files, making them complements rather than competitors.
About whisperX
m-bain/whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Builds on OpenAI's Whisper by combining faster-whisper for batched GPU inference (70x speedup) with wav2vec2 forced phoneme alignment to achieve sub-word timing accuracy. Integrates pyannote-audio for speaker diarization and includes VAD preprocessing to reduce hallucinations while maintaining quality. Supports multiple languages with automatic language-specific alignment model selection from HuggingFace and torchaudio.
About whisperVideo
showlab/whisperVideo
Find out who said what in the video.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work