20w+ speakers in training data？

yeyupiaoling / VoiceprintRecognition-Pytorch

This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the same time, this project also supports MelSpectrogram, Spectrogram data preprocessing methods

Apache License 2.0

791 stars 124 forks source link

20w+ speakers in training data？ #71

Closed MM-0712 closed 6 hours ago

MM-0712 commented 6 hours ago

@yeyupiaoling 大佬，有两个问题请教下： 1、文档里写的 20w + 说话人训练集都是开源的吗？ 2、20w + 说话人的训练集，是纯中文还是说混合了其他语种数据呢？感谢回答！

yeyupiaoling commented 6 hours ago

这个是阿里不开源的一个数据集。只有中文。

MM-0712 commented 6 hours ago

从 3d-speaker 上找到了