Word alignment error relative to SNR. See 🧵for details.
3
2
4
96
- WhisperX github.com/m-bain/whisperX WhisperX performs forced alignment with an external phoneme/CTC aligner, typically a wav2vec2-based model, to align a known transcript to the waveform and recover word timestamps.

Mar 25, 2026 · 7:51 PM UTC

2
60