[WIP] add SpeechT5 model (#18922)

* make SpeechT5 model by copying Wav2Vec2

* add paper to docs

* whoops added docs in wrong file

* remove SpeechT5Tokenizer + put CTC back in the name

* remove deprecated class

* remove unused docstring

* delete SpeechT5FeatureExtractor, use Wav2Vec2FeatureExtractor instead

* remove classes we don't need right now

* initial stab at speech encoder prenet

* add more speech encoder prenet stuff

* improve SpeechEncoderPrenet

* add encoder (not finished yet)

* add relative position bias to self-attention

* add encoder CTC layers

* fix formatting

* add decoder from BART, doesn't work yet

* make it work with generate loop

* wrap the encoder into a speech encoder class

* wrap the decoder in a text decoder class

* changed my mind

* changed my mind again ;-)

* load decoder weights, make it work

* add weights for text decoder postnet

* add SpeechT5ForCTC model that uses only the encoder

* clean up EncoderLayer and DecoderLayer

* implement _init_weights in SpeechT5PreTrainedModel

* cleanup config + Encoder and Decoder

* add head + cross attention masks

* improve doc comments

* fixup

* more cleanup

* more fixup

* TextDecoderPrenet works now, thanks Kendall

* add CTC loss

* add placeholders for other pre/postnets

* add type annotation

* fix freeze_feature_encoder

* set padding tokens to 0 in decoder attention mask

* encoder attention mask downsampling

* remove features_pen calculation

* disable the padding tokens thing again

* fixup

* more fixup

* code review fixes

* rename encoder/decoder wrapper classes

* allow checkpoints to be loaded into SpeechT5Model

* put encoder into wrapper for CTC model

* clean up conversion script

* add encoder for TTS model

* add speech decoder prenet

* add speech decoder post-net

* attempt to reconstruct the generation loop

* add speech generation loop

* clean up generate_speech

* small tweaks

* fix forward pass

* enable always dropout on speech decoder prenet

* sort declaration

* rename models

* fixup

* fix copies

* more fixup

* make consistency checker happy

* add Seq2SeqSpectrogramOutput class

* doc comments

* quick note about loss and labels

* add HiFi-GAN implementation (from Speech2Speech PR)

* rename file

* add vocoder to TTS model

* improve vocoder

* working on tokenizer

* more better tokenizer

* add CTC tokenizer

* fix decode and batch_code in CTC tokenizer

* fix processor

* two processors and feature extractors

* use SpeechT5WaveformFeatureExtractor instead of Wav2Vec2

* cleanup

* more cleanup

* even more fixup

* notebooks

* fix log-mel spectrograms

* support reduction factor

* fixup

* shift spectrograms to right to create decoder inputs

* return correct labels

* add labels for stop token prediction

* fix doc comments

* fixup

* remove SpeechT5ForPreTraining

* more fixup

* update copyright headers

* add usage examples

* add SpeechT5ProcessorForCTC

* fixup

* push unofficial checkpoints to hub

* initial version of tokenizer unit tests

* add slow test

* fix failing tests

* tests for CTC tokenizer

* finish CTC tokenizer tests

* processor tests

* initial test for feature extractors

* tests for spectrogram feature extractor

* fixup

* more fixup

* add decorators

* require speech for tests

* modeling tests

* more tests for ASR model

* fix imports

* add fake tests for the other models

* fixup

* remove jupyter notebooks

* add missing SpeechT5Model tests

* add missing tests for SpeechT5ForCTC

* add missing tests for SpeechT5ForTextToSpeech

* sort tests by name

* fix Hi-Fi GAN tests

* fixup

* add speech-to-speech model

* refactor duplicate speech generation code

* add processor for SpeechToSpeech model

* add usage example

* add tests for speech-to-speech model

* fixup

* enable gradient checkpointing for SpeechT5FeatureEncoder

* code review

* push_to_hub now takes repo_id

* improve doc comments for HiFi-GAN config

* add missing test

* add integration tests

* make number of layers in speech decoder prenet configurable

* rename variable

* rename variables

* add auto classes for TTS and S2S

* REMOVE CTC!!!

* S2S processor does not support save/load_pretrained

* fixup

* these models are now in an auto mapping

* fix doc links

* rename HiFiGAN to HifiGan, remove separate config file

* REMOVE auto classes

* there can be only one

* fixup

* replace assert

* reformat

* feature extractor can process input and target at same time

* update checkpoint names

* fix commit hash

README_ja.md

@@ -349,7 +349,7 @@ Flax、PyTorch、TensorFlowをcondaでインストールする方法は、それ
 1. **[ELECTRA](https://huggingface.co/docs/transformers/model_doc/electra)** (Google Research/Stanford University から) Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning から公開された研究論文: [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555)
 1. **[EncoderDecoder](https://huggingface.co/docs/transformers/model_doc/encoder-decoder)** (Google Research から) Sascha Rothe, Shashi Narayan, Aliaksei Severyn から公開された研究論文: [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://arxiv.org/abs/1907.12461)
 1. **[ERNIE](https://huggingface.co/docs/transformers/model_doc/ernie)** (Baidu から) Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, Hua Wu から公開された研究論文: [ERNIE: Enhanced Representation through Knowledge Integration](https://arxiv.org/abs/1904.09223)
-1. **[ESM](https://huggingface.co/docs/transformers/model_doc/esm)** (Meta AI から) はトランスフォーマープロテイン言語モデルです.  **ESM-1b** は Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus から公開された研究論文: [Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences](https://www.pnas.org/content/118/15/e2016239118). **ESM-1v** は Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu and Alexander Rives　から公開された研究論文: [Language models enable zero-shot prediction of the effects of mutations on protein function](https://doi.org/10.1101/2021.07.09.450648). **ESM-2** と　**ESMFold** は Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, Alexander Rives から公開された研究論文: [Language models of protein sequences at the scale of evolution enable accurate structure prediction](https://doi.org/10.1101/2022.07.20.500902) 
+1. **[ESM](https://huggingface.co/docs/transformers/model_doc/esm)** (Meta AI から) はトランスフォーマープロテイン言語モデルです.  **ESM-1b** は Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus から公開された研究論文: [Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences](https://www.pnas.org/content/118/15/e2016239118). **ESM-1v** は Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu and Alexander Rives　から公開された研究論文: [Language models enable zero-shot prediction of the effects of mutations on protein function](https://doi.org/10.1101/2021.07.09.450648). **ESM-2** と　**ESMFold** は Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, Alexander Rives から公開された研究論文: [Language models of protein sequences at the scale of evolution enable accurate structure prediction](https://doi.org/10.1101/2022.07.20.500902)
 1. **[FLAN-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5)** (Google AI から) Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V から公開されたレポジトリー [google-research/t5x](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints) Le, and Jason Wei
 1. **[FlauBERT](https://huggingface.co/docs/transformers/model_doc/flaubert)** (CNRS から) Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab から公開された研究論文: [FlauBERT: Unsupervised Language Model Pre-training for French](https://arxiv.org/abs/1912.05372)
 1. **[FLAVA](https://huggingface.co/docs/transformers/model_doc/flava)** (Facebook AI から) Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela から公開された研究論文: [FLAVA: A Foundational Language And Vision Alignment Model](https://arxiv.org/abs/2112.04482)
@@ -362,8 +362,8 @@ Flax、PyTorch、TensorFlowをcondaでインストールする方法は、それ
 1. **[GPT NeoX](https://huggingface.co/docs/transformers/model_doc/gpt_neox)** (EleutherAI から) Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach から公開された研究論文: [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://arxiv.org/abs/2204.06745)
 1. **[GPT NeoX Japanese](https://huggingface.co/docs/transformers/model_doc/gpt_neox_japanese)** (ABEJA から) Shinya Otani, Takayoshi Makabe, Anuj Arora, and Kyo Hattori からリリース.
 1. **[GPT-2](https://huggingface.co/docs/transformers/model_doc/gpt2)** (OpenAI から) Alec Radford*, Jeffrey Wu*, Rewon Child, David Luan, Dario Amodei** and Ilya Sutskever** から公開された研究論文: [Language Models are Unsupervised Multitask Learners](https://blog.openai.com/better-language-models/)
-1. **[GPT-J](https://huggingface.co/docs/transformers/model_doc/gptj)** (EleutherAI から) Ben Wang and Aran Komatsuzaki から公開されたレポジトリー [kingoflolz/mesh-transformer-jax](https://github.com/kingoflolz/mesh-transformer-jax/) 
-1. **[GPT-Sw3](https://huggingface.co/docs/transformers/model_doc/gpt-sw3)** (AI-Sweden から) Ariel Ekgren, Amaru Cuba Gyllensten, Evangelia Gogoulou, Alice Heiman, Severine Verlinden, Joey Öhman, Fredrik Carlsson, Magnus Sahlgren から公開された研究論文: [Lessons Learned from GPT-SW3: Building the First Large-Scale Generative Language Model for Swedish](http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.376.pdf) 
+1. **[GPT-J](https://huggingface.co/docs/transformers/model_doc/gptj)** (EleutherAI から) Ben Wang and Aran Komatsuzaki から公開されたレポジトリー [kingoflolz/mesh-transformer-jax](https://github.com/kingoflolz/mesh-transformer-jax/)
+1. **[GPT-Sw3](https://huggingface.co/docs/transformers/model_doc/gpt-sw3)** (AI-Sweden から) Ariel Ekgren, Amaru Cuba Gyllensten, Evangelia Gogoulou, Alice Heiman, Severine Verlinden, Joey Öhman, Fredrik Carlsson, Magnus Sahlgren から公開された研究論文: [Lessons Learned from GPT-SW3: Building the First Large-Scale Generative Language Model for Swedish](http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.376.pdf)
 1. **[Graphormer](https://huggingface.co/docs/transformers/model_doc/graphormer)** (Microsoft から) Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, Tie-Yan Liu から公開された研究論文: [Do Transformers Really Perform Bad for Graph Representation?](https://arxiv.org/abs/2106.05234).
 1. **[GroupViT](https://huggingface.co/docs/transformers/model_doc/groupvit)** (UCSD, NVIDIA から) Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang から公開された研究論文: [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://arxiv.org/abs/2202.11094)
 1. **[Hubert](https://huggingface.co/docs/transformers/model_doc/hubert)** (Facebook から) Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed から公開された研究論文: [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://arxiv.org/abs/2106.07447)
@@ -427,6 +427,7 @@ Flax、PyTorch、TensorFlowをcondaでインストールする方法は、それ
 1. **[SegFormer](https://huggingface.co/docs/transformers/model_doc/segformer)** (NVIDIA から) Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo から公開された研究論文: [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203)
 1. **[SEW](https://huggingface.co/docs/transformers/model_doc/sew)** (ASAPP から) Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi から公開された研究論文: [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://arxiv.org/abs/2109.06870)
 1. **[SEW-D](https://huggingface.co/docs/transformers/model_doc/sew_d)** (ASAPP から) Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger, Yoav Artzi から公開された研究論文: [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://arxiv.org/abs/2109.06870)
+1. **[SpeechT5](https://huggingface.co/docs/transformers/main/model_doc/speecht5)** (Microsoft Research から) Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei. から公開された研究論文 [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://arxiv.org/abs/2110.07205)
 1. **[SpeechToTextTransformer](https://huggingface.co/docs/transformers/model_doc/speech_to_text)** (Facebook から), Changhan Wang, Yun Tang, Xutai Ma, Anne Wu, Dmytro Okhonko, Juan Pino から公開された研究論文: [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://arxiv.org/abs/2010.05171)
 1. **[SpeechToTextTransformer2](https://huggingface.co/docs/transformers/model_doc/speech_to_text_2)** (Facebook から), Changhan Wang, Anne Wu, Juan Pino, Alexei Baevski, Michael Auli, Alexis Conneau から公開された研究論文: [Large-Scale Self- and Semi-Supervised Learning for Speech Translation](https://arxiv.org/abs/2104.06678)
 1. **[Splinter](https://huggingface.co/docs/transformers/model_doc/splinter)** (Tel Aviv University から), Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson, Omer Levy から公開された研究論文: [Few-Shot Question Answering by Pretraining Span Selection](https://arxiv.org/abs/2101.00438)