Views
No views yet
iic/speech_campplus_speaker-diarization_common for youtube2notion Kaggle startup experiments.configuration.json (507 bytes, sha256 406f6ec313e6e359b6d8605afaa520a3180b5ac33ef2e4e90114a92e3f886dd1)config.yaml (538 bytes, sha256 dc99defb2de71fe20e800f14b5c644645607a63cffeb60b5c9f1321d621b61b9)onnx/asd.onnx (63208524 bytes, sha256 b020ff7104cad71e14a51c7cedfa614ded2de7befe5c73f88c50792a2933783c)onnx/face_recog_ir101.onnx (260698833 bytes, sha256 1695521d026730358b7304a35542a86dad2aa4cad4f8bc25043975f4b6f679fb)onnx/fqa.onnx (406114 bytes, sha256 4d0e02b72f987989b5fe0447745521e16067b10777b66a1fb89362fb1ca08183)onnx/version-RFB-320.onnx (1231013 bytes, sha256 68bbbaa1023629ab4967c735c133ec2d440d94941cdcb4e0d9c9cd2ab0c83c0d)README.md (5140 bytes, sha256 0fdaf6da924186e66b66cadf089a7b3b3c81c7c36fd8de5af8c17c1fd6db4f8b).gitattributes (1414 bytes, sha256 f3d04437c926962476701a7939d22f21400b4eb0bdd31a15f0012576f2d00932)
| 测试集 | DER |
|---|---|
| 2人真实对话测试集 | 4.7% |
| 2-10人真实对话测试集 | 8.0% |
1# 版本要求 modelscope version 升级至最新版本 funasr 升级至最新版本
2from modelscope.pipelines import pipeline
3sd_pipeline = pipeline(
4 task='speaker-diarization',
5 model='damo/speech_campplus_speaker-diarization_common',
6 model_revision='v1.0.0'
7)
8input_wav = 'https://modelscope.cn/api/v1/models/damo/speech_campplus_speaker-diarization_common/repo?Revision=master&FilePath=examples/2speakers_example.wav'
9result = sd_pipeline(input_wav)
10print(result)
11# 如果有先验信息,输入实际的说话人数,会得到更准确的预测结果
12result = sd_pipeline(input_wav, oracle_num=2)
13print(result)1git clone https://github.com/alibaba-damo-academy/3D-Speaker.git && cd 3D-Speaker
2conda create -n 3D-Speaker python=3.8
3conda activate 3D-Speaker
4pip install -r requirements.txt1cd egs/3dspeaker/speaker-diarization
2pip install -r requirements.txt
3bash run.sh