Help I have no idea how this works

I have some basic coding experience which makes this possible to understand in the first place but my ability to do anything beyond copy and paste is not there.

I could get some of my compsci friends to help me but I can’t always bother them for everything.

Basically I have a few issues. For one, with my level of understanding, if deepspeech doesn’t tell me to type wsl into the command prompt then I’m not going to know I should be doing that.

I’ve gotten deepspeech to output the transcribed audio file into a text file named output.txt but since then I’ve been unable to do that again.

My only objective is to create a simple process for transcribing batch audio files to text files in one go. I am trying to build something like… I have 50 short audio files. I want to build 50 text files with those texts and direct that output to somewhere.

I’m struggling to do that and I saw transcript.py which seemed to promise to do what I wanted. Well I can barely read it but I have no clue what to do with transcript.py.

I have tried my best to find solutions before coming here but I do NOT understand anything about python. For instance I tried this page Python transcriber from scratch. Okay well even though the author wrote it for beginners, it makes little sense and I have many questions. If someone can help me walk through the process and set up a sequence of failproof steps or to just give advice here that would be great.

DeepSpeech is no longer under active development, you may try coqui-stt instead (which is a kind of successor to DeepSpeech): https://stt.readthedocs.io/en/latest/

Basic knowledge of Linux and Python is still required, though.

1 Like

Thank you. Did not know that.