Transcription of an mp3 file into text (Speech Recognition)
In this tutorial I want to explain how to use Python to transcribe an mp3 file named p1.mp3 and extract text, step by step. The mp3 file is stored in input_dir.
Steps:
- Convert mp3 file to wave file format using ffmpeg
- Get the length of wav file you want to transcribe in milliseconds
- Split single wave file to multiple small wave files
- Get the list of small wave files
- Transcribe each small wave file
see details and codes in [https://github.com/yousef-seyfari/Transcribe-mp3-to-text-using-Python/blob/main/transcribe_mp3_to_text.ipynb]