pyannote-pipeline

import os from pyannote.audio import Pipeline # Ensure you have a Hugging Face access token set as an environment variable # and have accepted user conditions for 'pyannote/speaker-diarization-community-1' # on hf.co/pyannote/speaker-diarization-community-1 hf_token = os.environ.get('HUGGINGFACE_ACCESS_TOKEN', '') if not hf_token: print("Error: HUGGINGFACE_ACCESS_TOKEN environment variable not set.") print("Please create a token at hf.co/settings/tokens and set it.") exit() # Instantiate a pretrained speaker diarization pipeline try: pipeline = Pipeline.from_pretrained( "pyannote/speaker-diarization-community-1", token=hf_token ) except Exception as e: print(f"Failed to load pipeline: {e}") print("Make sure your Hugging Face token is valid and you've accepted user conditions.") exit() # Example: Apply the pipeline to an audio file (replace 'audio.wav' with your path) # For demonstration, we'll simulate a file path. # In a real scenario, you would have 'audio.wav' present. audio_file_path = "dummy_audio.wav" # Replace with actual audio file path # This part of the code is illustrative as 'dummy_audio.wav' won't exist. # You would typically pass a real audio file path here. print(f"Attempting to apply pipeline to {audio_file_path}...") # For actual execution, ensure 'ffmpeg' is installed and 'audio.wav' exists. # output = pipeline(audio_file_path) # print("Diarization results:") # for turn, speaker in output.speaker_diarization: # print(f"start={turn.start:.1f}s stop={turn.end:.1f}s speaker={speaker}") print("Pipeline loaded successfully. To run, replace 'dummy_audio.wav' with your audio file and ensure ffmpeg is installed.") print("Note: The actual application of the pipeline to 'dummy_audio.wav' is commented out as it requires a real audio file and ffmpeg.")