pyannote-audio

import os import torchaudio import torch import numpy as np import tempfile import shutil # 1. Create a dummy audio file for demonstration duration_seconds = 5 sample_rate = 16000 t = np.linspace(0, duration_seconds, int(sample_rate * duration_seconds), endpoint=False) audio_data = 0.5 * np.sin(2 * np.pi * 440 * t).astype(np.float32) temp_dir = tempfile.mkdtemp() dummy_audio_path = os.path.join(temp_dir, "dummy_audio.wav") torchaudio.save(dummy_audio_path, torch.from_numpy(audio_data).unsqueeze(0), sample_rate) # 2. Authenticate with Hugging Face Hub # Get your Hugging Face token from https://huggingface.co/settings/tokens # and set it as an environment variable `HF_TOKEN` or replace the placeholder. hf_token = os.environ.get("HF_TOKEN", "hf_YOUR_HUGGING_FACE_TOKEN_HERE") if hf_token == "hf_YOUR_HUGGING_FACE_TOKEN_HERE": print("WARNING: Please obtain a Hugging Face token from https://huggingface.co/settings/tokens ") print("and set the HF_TOKEN environment variable or replace the placeholder in the code.") print("Continuing with placeholder token; pipeline initialization might fail without proper authentication.") # 3. Import and initialize the Pyannote.audio Pipeline from pyannote.audio import Pipeline pipeline = Pipeline("pyannote/speaker-diarization-3.1", use_auth_token=hf_token) # 4. Prepare the audio input demo_file = {"uri": "dummy_conversation", "audio": dummy_audio_path} # 5. Run the speaker diarization di_result = pipeline(demo_file) # 6. Print the diarization result print("\nDiarization Result:") for turn, _, speaker in di_result.itertracks(yield_label=True): print(f"start={turn.start:.1f}s stop={turn.end:.1f}s speaker={speaker}") # 7. Clean up the dummy audio file shutil.rmtree(temp_dir) print(f"\nCleaned up temporary audio directory: {temp_dir}")