search

sandrohanea / whisper.net

Whisper.net. Speech to text made simple using Whisper Models
MIT License
505 stars 77 forks source link

Segments properties 'Start' and 'End' times are in seconds precision if transcription is done by using LargeV2 model. With Base model times are in ms precision #166

Closed Valdemaras closed 4 months ago

Valdemaras commented 4 months ago

Find out that changing strategy from greedy to beam search has fixed timestamp issue