No Time to LISTEN? AI Podcast Transcript!!!

[@AbhayTiwari]

Hey LittleCoder, Thanks for your wonderful efforts. I have been looking for opposite one(Text to Speech). I have to travel a lot. I wanted something which can record my research papers. Never found a good one. Will appreciate if you can share something like that.

[@prkssngowthamdora]

----> 2 from whisper.utils import write_vtt ImportError: cannot import name 'write_vtt' from 'whisper.utils' (/usr/local/lib/python3.8/dist-pa Iam getting this error , what should i do.

[@twobob]

use redux and clean it first maybe. Would be really nice if each sentence was time stamped. Solid guide.

[@1littlecoder]

Each sentence is time stamped when you download the vtt file. You can open that with any text editor

[@twobob]

@@1littlecoder Aye. just noticed. :)

[@dipanshumansingka]

Here you didnt mention about 30 seconds limitation like other earlier videos

[@Renatus_Eruditus]

Can this be modified to transcribe a podcast in realtime, live, with no time delay?

[@maheshc1417]

what if i have audio file of my interview in audio format and transcribing it in to text please tell me how to do it

[@nirannoel8509]

Hii, can i know how to detect the silence in the large audio file in the openai whsiper????can you please explain it.

[@dimorischinyui1875]

Hey guys please can anyone help me with this issue. I am trying to run whisper on my machine and I am getting this error in cmd. UserWarning: FP16 is not supported on CPU; using FP32 instead warnings.warn("FP16 is not supported on CPU; using FP32 instead"). I use a windows 10 with gpu RTX2060. Also it seems it runs on my cpu instead of NVIDIA GPU. I created a python virtual environment and pip installed whisper in that virtual environment just for more details.

[@davitmodebadze9707]

Have you tried ''pip install cuda-python"?