https://github.com/anirudhg07/audiotext_commands

https://github.com/anirudhg07/audiotext_commands

Last synced: 9 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/anirudhg07/audiotext_commands
• Owner: AnirudhG07
• License: other
• Created: 2023-11-20T19:49:40.000Z (almost 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-25T22:06:43.000Z (12 months ago)
• Last Synced: 2023-11-25T23:20:42.881Z (12 months ago)
• Language: Jupyter Notebook
• Size: 1.96 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Audio and Text Commands Python

This repository will have various Audio to Text or vice-versa codes in python.

It uses various libararies of python. Some of them maybe slow and faster versions will be updated.

I have used AssemblyAI in some of the programs! Thanks for an easy-to-use model!

# Why is this repository made?

This repository is made to support me in my First Semester Self-Made Project.

It involves various uses of Audio, Text and how to output them side by side, etc.

# Uses of Files 

- The mp3 and wav files are random english speech which i used in codes. Taken from kaggle, website's freely available files.

- speech to text converts your voice to text.

- audiofile_to_text1.py converts anyaudio to text, with various properties using AssemblyAI

- AudioStampsByWord returns timestamps for each in milliseconds.

- gtts_sound_translate is gtts people know in love.

- pyttsx3.py is python documentation of pyttsx3 as it is, which i use to remember command lines.

- WhisperAI-manual.py is simply docs of OPENAI of whisper, which converts text to speech(Advantage: various voices, can control speed)

Created by Anirudh Gupta