handler.py

from typing import  Dict
from pyannote.audio import Pipeline
from transformers.pipelines.audio_utils import ffmpeg_read
import torch 
import base64
import numpy as np

SAMPLE_RATE = 16000

class EndpointHandler():
    def __init__(self, path=""):
        # load the model
        self.pipeline = Pipeline.from_pretrained("philschmid/pyannote-speaker-diarization-endpoint")

    def __call__(self, data: Dict[str, bytes]) -> Dict[str, str]:
        """
        Args:
            data (:obj:):
                includes the deserialized audio file as bytes
        Return:
            A :obj:`dict`:. base64 encoded image
        """
        # process input
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None) # min_speakers=2, max_speakers=5

        # decode the base64 audio data
        audio_data = base64.b64decode(inputs)
        audio_nparray = np.frombuffer(audio_data, dtype=np.int16)
        
        # prepare pynannote input
        audio_tensor= torch.from_numpy(audio_nparray).unsqueeze(0)
        pyannote_input = {"waveform": audio_tensor, "sample_rate": SAMPLE_RATE}

        # apply pretrained pipeline
        # pass inputs with all kwargs in data
        if parameters is not None:
            diarization = self.pipeline(pyannote_input, **parameters)
        else:
            diarization = self.pipeline(pyannote_input)

        # postprocess the prediction
        processed_diarization = [
            {"label": str(label), "start": str(segment.start), "stop": str(segment.end)}
            for segment, _, label in diarization.itertracks(yield_label=True)
        ]
        
        return {"diarization": processed_diarization}