openai-whisper

import whisper import os # Ensure you have an audio file, e.g., 'audio.mp3' # For demonstration, let's create a dummy file if it doesn't exist dummy_audio_path = 'dummy_audio.mp3' if not os.path.exists(dummy_audio_path): # This is just a placeholder, in a real scenario you'd use a valid audio file print(f"Please ensure a valid audio file named '{dummy_audio_path}' exists for transcription.") # Example: you might download a small audio file here # For real use, replace this with your actual audio file. # For this quickstart, we'll assume it exists or the user provides one. # To make it runnable for testing, let's create a minimal WAV (requires scipy) try: from scipy.io.wavfile import write import numpy as np samplerate = 16000 # 16 kHz duration = 1.0 # 1 second frequency = 440 # A4 note t = np.linspace(0., duration, int(samplerate * duration), endpoint=False) amplitude = np.iinfo(np.int16).max * 0.5 data = amplitude * np.sin(2. * np.pi * frequency * t) write(dummy_audio_path, samplerate, data.astype(np.int16)) print(f"Created a dummy audio file: {dummy_audio_path}") except ImportError: print("scipy not found. Cannot create dummy audio. Please provide your own audio.mp3.") exit() # Load a Whisper model (e.g., 'base', 'small', 'medium', 'large') # 'tiny' or 'base' are good for quick tests, 'large' for best accuracy. # The model will be downloaded on first use. print("Loading Whisper model...") model = whisper.load_model("base") # You can choose 'tiny', 'base', 'small', 'medium', 'large' # Transcribe the audio file print(f"Transcribing {dummy_audio_path}...") result = model.transcribe(dummy_audio_path) # Print the transcription print("Transcription:") print(result["text"])