From e0bd877ac08d6ef61c23bdc9fd2d6d7624ef2b4f Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 14 三月 2023 14:36:31 +0800
Subject: [PATCH] Merge pull request #226 from alibaba-damo-academy/dev_dzh
---
egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py | 26 ++++++++++++++++++++++++++
funasr/models/pooling/statistic_pooling.py | 2 +-
2 files changed, 27 insertions(+), 1 deletions(-)
diff --git a/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py
new file mode 100644
index 0000000..3cb31cf
--- /dev/null
+++ b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py
@@ -0,0 +1,26 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+# 鍒濆鍖栨帹鐞� pipeline
+# 褰撲互鍘熷闊抽浣滀负杈撳叆鏃朵娇鐢ㄩ厤缃枃浠� sond.yaml锛屽苟璁剧疆 mode 涓簊ond_demo
+inference_diar_pipline = pipeline(
+ mode="sond_demo",
+ num_workers=0,
+ task=Tasks.speaker_diarization,
+ diar_model_config="sond.yaml",
+ model='damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch',
+ sv_model="damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch",
+ sv_model_revision="master",
+)
+
+# 浠� audio_list 浣滀负杈撳叆锛屽叾涓涓�涓煶棰戜负寰呮娴嬭闊筹紝鍚庨潰鐨勯煶棰戜负涓嶅悓璇磋瘽浜虹殑澹扮汗娉ㄥ唽璇煶
+audio_list = [[
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record.wav",
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_A.wav",
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B.wav",
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B1.wav"
+]]
+
+results = inference_diar_pipline(audio_in=audio_list)
+for rst in results:
+ print(rst["value"])
diff --git a/funasr/models/pooling/statistic_pooling.py b/funasr/models/pooling/statistic_pooling.py
index 97f8a24..8f85de9 100644
--- a/funasr/models/pooling/statistic_pooling.py
+++ b/funasr/models/pooling/statistic_pooling.py
@@ -82,7 +82,7 @@
tt = xs_pad.shape[2]
num_chunk = int(math.ceil(tt / pooling_stride))
pad = pooling_size // 2
- if xs_pad.shape == 4:
+ if len(xs_pad.shape) == 4:
features = F.pad(xs_pad, (0, 0, pad, pad), "reflect")
else:
features = F.pad(xs_pad, (pad, pad), "reflect")
--
Gitblit v1.9.1