update speaker infer

modelscope · Jan 22, 2024 · 9285e7d · 9285e7d
1 parent 3919d74
commit 9285e7d
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/funasr/auto/auto_model.py b/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 @@ def inference_with_vad(self, input, input_len=None, **cfg):
                     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]