GitHub archive, repository 31 of 66
whisper
Tiny script transcribing a WAV file with OpenAI Whisper 'small', with README notes comparing output against reference text.
- What this is
- Experiment. A small exploration of a tool, model or library.
- Category
- Voice
- Main language
- Python
- Created
- 1 May 2025
- Last pushed
- 1 May 2025
Description on GitHub
This project uses OpenAI Whisper to transcribe audio files and evaluate the accuracy of different transcription outputs. The main goal is to analyze how Whisper handles subtle variations in pronunciation, clarity, and accent.
Found in the code
Iterations of the same idea
- hope 14 May 2025
- Parler-TTS 2 May 2025
- Piper-tts 2 May 2025
More in Voice
- bruh-benki Experiment
- MindLoom Original
- eleven_sample Experiment
This page is generated from public GitHub metadata plus a short note I wrote after reviewing the repository. Back to the full archive