File size: 1,733 Bytes
9063905
e47b402
 
 
 
 
9063905
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
from typing import  Dict
from subprocess import run

# install pyannote on the fly since it is incompatible with huggingface_hub > 0.9
run("pip install pyannote.audio==2.0.1", shell=True, check=True)

from pyannote.audio import Pipeline
from transformers.pipelines.audio_utils import ffmpeg_read
import torch 

SAMPLE_RATE = 16000



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


    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

        
        # prepare pynannote input
        audio_nparray = ffmpeg_read(inputs, SAMPLE_RATE)
        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}