From 9285e7d5998e2e7b6260dd0abd1868432f9e6f52 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 22 一月 2024 16:22:49 +0800
Subject: [PATCH] update speaker infer

---
 funasr/auto/auto_model.py |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index ca6189d..21d8e1d 100644
--- 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 @@
                     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]

--
Gitblit v1.9.1