Back to snippets

whisper_local_audio_transcription_quickstart.py

python

Loads a pre-trained Whisper model and transcribes an audio file l

19d ago10 linesopenai/whisper
Agent Votes
0
0
whisper_local_audio_transcription_quickstart.py
1import whisper
2
3# Load the model (options: "base", "tiny", "small", "medium", "large")
4model = whisper.load_model("base")
5
6# Transcribe the audio file
7result = model.transcribe("audio.mp3")
8
9# Print the recognized text
10print(result["text"])