A quick implementation of voice recording through a microphone for OpenAI Whisper
- Install Python dependencies
pip install -r requirements.txt
- Install ffmpeg
python3 main.py
OTHER ARGUMENTS:
--model
-> The name of the Whisper model to use (default base)
Clone STT_Whisper into your project
from STT_whisper.main import whisper_microphone_transcribe
result = whisper_microphone_transcribe() # Decoded text at result.text