Skip to content

hudsonshoffih/transcript-generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Transcript Generator

Overview

This project provides a deep learning-based system to generate text transcripts from YouTube videos using Automatic Speech Recognition (ASR). By leveraging Hugging Face's Wav2Vec2 model, the project converts spoken words from video into accurate text. It focuses on fine-tuning the ASR model to handle a variety of accents, languages, and noisy environments effectively.

Features

  • Audio Extraction: Downloads and extracts audio from YouTube videos.
  • Speech-to-Text: Transforms the audio into text using a fine-tuned Wav2Vec2 model.
  • Customization: The model can be fine-tuned for improved accuracy on specific datasets or types of speech.
  • Performance: Evaluates accuracy and speed of transcription across different audio qualities.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors