Video Transcription
Project description
Video Transcription Script - COPYPy
This script extracts audio from a video file, transcribes the audio into text using Google's Speech Recognition API And OpenAi Whisper Model, and writes the transcribed text to a file.
Dependencies
- pydub
- speech_recognition
You can install these packages using pip:
pip install copypy
Usage
python -m copypy <video_path> <output_path>
Where:
<video_path>
is the path to the video file you want to transcribe.<output_path>
is the path where the transcribed text will be written to.
The script currently supports MP4 video files and transcribes audio to Spanish. You can modify the script to support other video formats or languages.
Next, you might want to add more details to your README, such as a section on how to contribute to your project, or a section detailing any known issues or limitations of your script.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
copypy-0.0.9.tar.gz
(3.0 kB
view hashes)
Built Distribution
copypy-0.0.9-py3-none-any.whl
(3.5 kB
view hashes)