This reverts commit 6e0044be.

*merge develop into speechx

* iSTFTNet implementation based on hifigan, not affect the function and execution of HIFIGAN

* modify the comment in iSTFT.yaml

* add the comments in hifigan

* iSTFTNet implementation based on hifigan, not affect the function and execution of HIFIGAN

* modify the comment in iSTFT.yaml

* add the comments in hifigan

* add iSTFTNet.md

* modify the format of iSTFTNet.md

* modify iSTFT.yaml and hifigan.py

* Format code using pre-commit

* modify hifigan.py,delete the unused self.istft_layer_id , move the self.output_conv behind else, change conv_post to output_conv

* update iSTFTNet_csmsc_ckpt.zip download link

* modify iSTFTNet.md

* modify hifigan.py and iSTFT.yaml

* modify iSTFTNet.md

* remove pad op in static model by replace F.pad with nn.Pad1D and nn.Pad2D

* fix variable names

* add note

Co-authored-by: N0x45f <wangzhen45@baidu.com>

soft link for shell in example, add skip_copy_wave in norm stage of GANVocoders to save disk

* Add export2lite, test=tts

* add tts paddlelite x86 inference, test=tts

* update released_model.md, test=tts

* add paddlelite in setup.py

* update

* code for training vits voice clone on aishell3.
Co-authored-by: TianYuan <white-sky@qq.com>

* fix ONNXRuntimeError Specify data type (int64),test=tts

* Tactron2→Tacotron2 ,test=doc