need help with setting up an audio to text thing

[junior marlin]

https://github.com/openai/whisper

[somber sparrow]

Can you give us some more details on what sort of thing you need help with?

[junior marlin]

I want to convert an mp4 file or mp3 I forgot what it was into a transcript for myself so I can read it instead of listen to it

[somber sparrow]

I see! What sort of things have you tried on your own with the whisper library? Have you been running into problems?

[junior marlin]

I didn't understand how to even start the coding bit or anything

[somber sparrow]

Are you familiar with any programming languages to start?

[junior marlin]

I need a step by step way of doing it with a person

[junior marlin]

python

yes

I have no knowledge of coding frankly

[somber sparrow]

I see, I think the README docs themselves are a decent way to start, for example it shows you how to transcribe:

import whisper

model = whisper.load_model("base")
result = model.transcribe("audio.mp3")
print(result["text"])

But unfortunately for a project like this, you'll need a bit more programming background and some more research, it'll be a bunch of trial and error but you can definitely do it

[junior marlin]

I can't do it

(I don't want this to come as rude but ) I know what I can and can't do and programming and coding is like learning a dif language that's something which I can't do