Skip to content

prasanth-99/Audio_text

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 

Repository files navigation

Audio_text


For this Audio to text converting tool. I used Whisper launced by Open_AI Following are the requirements of tools and the installation steps for to configure whisper

Tool Requirements:


  1. Install Python-version-3.10

  2. Install Pytorch

image

  1. Install CUDA-11.6

image

  1. install ffmpeg
pip uninstall ffmpeg
pip uninstall ffmpeg-python

pip install ffmpeg-python

  1. Whisper Installation
pip install -U openai-whisper
  1. Upgrade the package:

pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git

pip install setuptools-rust

This marks completion of setup.

After this set the root directory with the destination where the Audio files are stored. Change the format of the Audio files if necessary.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages