app.py

import gradio as gr
#from pyannote.audio import Pipeline
import tempfile
import os
from pyannote.audio import Pipeline

pipeline = Pipeline.from_pretrained(
    "pyannote/speaker-diarization-community-1", token=os.getenv('HF_TOKEN')
)

def diarize(audio_file_path):
    """
    Perform speaker diarization on uploaded audio file.
    """


    # Run diarization
    diarization = pipeline(audio_file_path)

    # Collect readable results
    results = []
    for turn, speaker in diarization.speaker_diarization:
        results.append(
            f"{speaker} speaks between t={turn.start:.3f}s and t={turn.end:.3f}s"
        )
    return "\n".join(results)


# 🎛️ Gradio interface
demo = gr.Interface(
    fn=diarize,
    inputs=gr.Audio(type="filepath", label="Upload Audio (.wav)"),
    outputs=gr.Textbox(label="Speaker Segments"),
    title="🎙️ Speaker Diarization Demo",
    description="Upload an audio file and detect who speaks when using Pyannote Audio."
)

if __name__ == "__main__":
    demo.launch()