🤖 Model 🔊
quinten-kamphuis/forced-alignment
Align audio to a given transcript, returning word-level start and end timestamps. Input an audio clip and its script; ou...
Found 2 models (showing 1-2)
Align audio to a given transcript, returning word-level start and end timestamps. Input an audio clip and its script; ou...
Transcribe audio to text with per-word timestamps. Outputs the full transcript, time-coded segments, detected language,...