from pyannote.audio import Pipeline
import gradio as gr

def diarization():
    pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization")
    output = pipeline("audio.wav")
    answer = ""
    for turn, _, speaker in output.itertracks(yield_label=True):
        answer += "{} said something starting from {} and ends on {}\n".format(speaker,turn.start,turn.end)
    return answer

app = gr.Interface(fn=diarization, inputs="audio", outputs="text")
app.launch()