| # using whisper to transcribe audio files | |
| import whisper | |
| import os | |
| def transcribe_audio(file_path, model_size="base"): | |
| """ | |
| Transcribe audio file using Whisper model. | |
| Args: | |
| file_path (str): Path to the audio file. | |
| model_size (str): Size of the Whisper model to use. Options are "tiny", "base", "small", "medium", "large". | |
| Returns: | |
| str: Transcription of the audio file. | |
| """ | |
| # Load the Whisper model | |
| model = whisper.load_model(model_size) | |
| # Transcribe the audio file | |
| result = model.transcribe(file_path, fp16=False) | |
| # Return the transcription | |
| return result["text"] |