I have a text file. I generate a voice-over wav file using TTS. How can I generate subtitle for it?

Asked Apr 10 '23 at 18:15

Active Apr 10 '23 at 18:18

Viewed 142 times

I have a text file. I generate a voice-over wav file using TTS. How can I generate subtitles for it? I use Azure and/or Coqui-AI TTS depending on the case.

I currently generate subtitles using the offline openai-Whisper model. But, it doesn't recognize words correctly. How can I compare and fix them? Or do you have any alternative solutions for it?

Since I have the original text file, it should be easy to compare and correct the misrecognized words, but I am not able to do it.

edited Apr 10 '23 at 18:18

asked Apr 10 '23 at 18:15

Serhan

Why don't you just use the original text file? – Tim Roberts Apr 10 '23 at 18:19
How can I get time stamps for them? Or how can I compare and correct the misrecognized words? – Serhan Apr 10 '23 at 18:23
You can use Whisper by OpenAI, or AssemblyAI https://www.assemblyai.com/products/core-transcription – Ahmad Anis Apr 10 '23 at 18:47
actually, i have mentioned that. It doesnt recognize all words correctly. I need the correct that words. – Serhan Apr 10 '23 at 18:51

I have a text file. I generate a voice-over wav file using TTS. How can I generate subtitle for it?

0 Answers0