Open brettdavies opened 2 months ago
Hi @brettdavies👋
By default, confidence scores are also being added to the output after Alignment. Eg: Checkout the sample output for an audio sample.json, it has score
for each of the segments. Please feel free to correct me if I'm wrong here:)
Regards, Nikhil
Hi @nkilm! I found your repo, which does most of what I want. Did you happen to implement the confidence score functionality from the whisperX library? If not, I'm happy to do the work if you can point me in the right direction.
🎯 Accurate word-level timestamps using wav2vec2 alignment
Kind regards.