From 0e3b3e0482b1117738b3d45d0fe9078ec963159e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=BF=97=E6=B5=A9?= Date: Fri, 7 Apr 2023 19:01:41 +0800 Subject: [PATCH] add infer test for sond models --- .../infer.py} | 7 +++-- .../infer.py | 26 +++++++++++++++++++ 2 files changed, 29 insertions(+), 4 deletions(-) rename egs_modelscope/speaker_diarization/{speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py => speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/infer.py} (94%) create mode 100644 egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/infer.py 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-en-us-callhome-8k-n16k4-pytorch/infer.py similarity index 94% rename from egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py rename to egs_modelscope/speaker_diarization/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/infer.py index 3cb31cfb7..5f4563dbc 100644 --- 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-en-us-callhome-8k-n16k4-pytorch/infer.py @@ -14,13 +14,12 @@ inference_diar_pipline = pipeline( ) # 以 audio_list 作为输入，其中第一个音频为待检测语音，后面的音频为不同说话人的声纹注册语音 -audio_list = [[ +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"]) +print(results) diff --git a/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/infer.py b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/infer.py new file mode 100644 index 000000000..db22c184d --- /dev/null +++ b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/infer.py @@ -0,0 +1,26 @@ +from modelscope.pipelines import pipeline +from modelscope.utils.constant import Tasks + +# 初始化推理 pipeline +# 当以原始音频作为输入时使用配置文件 sond.yaml，并设置 mode 为sond_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-zh-cn-alimeeting-16k-n16k4-pytorch', + sv_model="damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch", + sv_model_revision="master", +) + +# 以 audio_list 作为输入，其中第一个音频为待检测语音，后面的音频为不同说话人的声纹注册语音 +audio_list = [ + "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/record.wav", + "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk1.wav", + "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk2.wav", + "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk3.wav", + "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk4.wav", +] + +results = inference_diar_pipline(audio_in=audio_list) +print(results)