update speaker infer

shixian.shi

2024-01-22 9285e7d5998e2e7b6260dd0abd1868432f9e6f52

 funasr/auto/auto_model.py

@@ -6,6 +6,7 @@
import string
import logging
import os.path
import numpy as np
from tqdm import tqdm
from omegaconf import DictConfig, OmegaConf, ListConfig

@@ -334,7 +335,7 @@
                    for _b in range(len(speech_j)):
                        vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0,
                                        sorted_data[beg_idx:end_idx][_b][0][1]/1000.0,
                                        speech_j[_b]]]
                                        np.array(speech_j[_b])]]
                        segments = sv_chunk(vad_segments)
                        all_segments.extend(segments)
                        speech_b = [i[2] for i in segments]
@@ -391,7 +392,7 @@
            if self.punc_model is not None:
                self.punc_kwargs.update(cfg)
                punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg)
                result["text_with_punc"] = punc_res[0]["text"]
                result["text"] = punc_res[0]["text"]
                     
            # speaker embedding cluster after resorted
            if self.spk_model is not None: