[WIP]Add speaker recognition example

[KPatr1ck]

PR types

New feature

PR changes

dataset, model, example

Describe

• Model:
  • Add ECAPA-TDNN model
• Datasets:
  • Add VoxCeleb1 dataset
  • Add OpenRIRNoise dataset
  • Update api usage in other datasets
• Data Augment
  • Add on the fly data augment
• Loss
  • Add Additive Angular Margin Loss
• Scripts
  • Add training script of speaker identification
  • Add speaker verification and EER evaluation

[ZeyuChen]

@KPatr1ck any update？

[KPatr1ck]

@KPatr1ck any update？

数据集，模型，loss，训练和预测脚本已齐。
全量数据在训练对齐中。

[KPatr1ck]

@ZeyuChen @ranchlai
Doc string持续补齐中，model、dataset、训练预测脚本可以先reivew一波～

[ZeyuChen]

使用标准的注释
# NOTE(xxxxxgithuid or username): blabla

[ZeyuChen]

convolved1d和conv1d的区别是什么？

[ZeyuChen]

参考SpeechBrain看这些基础function是否有注释

[ZeyuChen]

trainning -> training

[ZeyuChen]

Need more comments for dataset source

[ZeyuChen]

More dataset source comments.

[ZeyuChen]

Move this model implementation to examples if without pretrained weight.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}