audiolm pytorch 다운로드 - audiolm pytorch 소스 코드 다운로드

AudioLM - Pytorch

Pytorch에서 Google Research의 오디오 생성에 대한 언어 모델링 접근 방식인 AudioLM 구현

또한 T5를 사용하여 분류자 무료 안내를 통해 조건화 작업을 확장합니다. 이를 통해 논문에서는 제공되지 않는 텍스트-오디오 또는 TTS를 수행할 수 있습니다. 예, 이는 VALL-E가 이 저장소에서 훈련될 수 있음을 의미합니다. 본질적으로 동일합니다.

이 작품을 공개적으로 복제하는 데 관심이 있다면 가입하세요.

이제 이 저장소에는 SoundStream의 MIT 라이센스 버전도 포함되어 있습니다. 또한 이 글을 쓰는 시점에 MIT 라이선스를 받은 EnCodec과도 호환됩니다.

업데이트: AudioLM은 본질적으로 새로운 MusicLM에서 음악 생성을 '해결'하는 데 사용되었습니다.

미래에는 이 영화 클립이 더 이상 의미가 없게 될 것입니다. 대신 AI를 호출하면 됩니다.

감사

Stability.ai 작업 및 오픈소스 최첨단 인공지능 연구에 대한 아낌없는 후원
? 놀라운 가속 및 변압기 라이브러리를 위한 Huggingface
Fairseq용 MetaAI 및 자유 라이센스
@eonglints와 Joseph은 전문적인 조언과 전문 지식은 물론 끌어오기 요청도 제공했습니다!
사운드스트림 디버깅에 도움을 주신 @djqualia, @yigityu, @inspirit 및 @BlackFox1197
코드를 검토하고 버그 수정을 제출해 주신 Allen 및 LWprogramming님!
다중 스케일 판별기 다운샘플링 문제를 찾아내고 사운드스트림 트레이너를 개선해 주신 Ilya
사운드스트림에서 누락된 손실을 식별하고 적절한 멜 스펙트로그램 하이퍼파라미터를 안내해 준 Andrey
훈련 사운드스트림을 통해 결과를 공유하고 로컬 어텐션 위치 임베딩과 관련된 몇 가지 문제를 해결한 Alejandro와 Ilya
인코딩 호환성을 추가하는 LW 프로그래밍!
FineTransformer 에서 샘플링할 때 EOS 토큰 처리 문제를 찾기 위한 LWprogramming !
@YoungloLee는 보폭을 고려하지 않는 패딩과 관련된 사운드 스트림에 대한 1D 인과 컨볼루션의 큰 버그를 식별했습니다!
Soundstream의 다중 스케일 판별기의 일부 불일치를 지적한 Hayden

설치하다

$ pip install audiolm-pytorch

용법

사운드스트림 및 인코딩

신경 코덱에는 두 가지 옵션이 있습니다. 사전 훈련된 24kHz Encodec을 사용하려면 다음과 같이 Encodec 객체를 생성하면 됩니다.

 from audiolm_pytorch import EncodecWrapper
encodec = EncodecWrapper ()
# Now you can use the encodec variable in the same way you'd use the soundstream variables below.

그렇지 않으면 원본 논문에 더 충실하려면 SoundStream 사용할 수 있습니다. 첫째, SoundStream 대규모 오디오 데이터 모음에 대해 교육을 받아야 합니다.

 from audiolm_pytorch import SoundStream , SoundStreamTrainer

soundstream = SoundStream (
    codebook_size = 4096 ,
    rq_num_quantizers = 8 ,
    rq_groups = 2 ,                       # this paper proposes using multi-headed residual vector quantization - https://arxiv.org/abs/2305.02765
    use_lookup_free_quantizer = True ,    # whether to use residual lookup free quantization - there are now reports of successful usage of this unpublished technique
    use_finite_scalar_quantizer = False , # whether to use residual finite scalar quantization
    attn_window_size = 128 ,              # local attention receptive field at bottleneck
    attn_depth = 2                       # 2 local attention transformer blocks - the soundstream folks were not experts with attention, so i took the liberty to add some. encodec went with lstms, but attention should be better
)

trainer = SoundStreamTrainer (
    soundstream ,
    folder = '/path/to/audio/files' ,
    batch_size = 4 ,
    grad_accum_every = 8 ,         # effective batch size of 32
    data_max_length_seconds = 2 ,  # train on 2 second audio
    num_train_steps = 1_000_000
). cuda ()

trainer . train ()

# after a lot of training, you can test the autoencoding as so

soundstream . eval () # your soundstream must be in eval mode, to avoid having the residual dropout of the residual VQ necessary for training

audio = torch . randn ( 10080 ). cuda ()
recons = soundstream ( audio , return_recons_only = True ) # (1, 10080) - 1 channel

그러면 훈련된 SoundStream 오디오용 일반 토크나이저로 사용할 수 있습니다.

 audio = torch . randn ( 1 , 512 * 320 )

codes = soundstream . tokenize ( audio )

# you can now train anything with the codebook ids

recon_audio_from_codes = soundstream . decode_from_codebook_indices ( codes )

# sanity check

assert torch . allclose (
    recon_audio_from_codes ,
    soundstream ( audio , return_recons_only = True )
)

AudioLMSoundStream 및 MusicLMSoundStream 각각 가져와서 AudioLM 및 MusicLM 에 특정한 사운드 스트림을 사용할 수도 있습니다.

 from audiolm_pytorch import AudioLMSoundStream , MusicLMSoundStream

soundstream = AudioLMSoundStream (...) # say you want the hyperparameters as in Audio LM paper

# rest is the same as above

버전 0.17.0 부터 이제 구성을 기억할 필요 없이 SoundStream 의 클래스 메서드를 호출하여 체크포인트 파일에서 로드할 수 있습니다.

 from audiolm_pytorch import SoundStream

soundstream = SoundStream . init_and_load_from ( './path/to/checkpoint.pt' )

가중치 및 편향 추적을 사용하려면 먼저 SoundStreamTrainer 에서 use_wandb_tracking = True 설정한 후 다음을 수행하세요.

 trainer = SoundStreamTrainer (
    soundstream ,
    ...,
    use_wandb_tracking = True
)

# wrap .train() with contextmanager, specifying project and run name

with trainer . wandb_tracker ( project = 'soundstream' , run = 'baseline' ):
    trainer . train ()

계층적 변환기

그런 다음 세 개의 별도 변환기( SemanticTransformer , CoarseTransformer , FineTransformer )를 훈련해야 합니다.

전. SemanticTransformer

 import torch
from audiolm_pytorch import HubertWithKmeans , SemanticTransformer , SemanticTransformerTrainer

# hubert checkpoints can be downloaded at
# https://github.com/facebookresearch/fairseq/tree/main/examples/hubert

wav2vec = HubertWithKmeans (
    checkpoint_path = './hubert/hubert_base_ls960.pt' ,
    kmeans_path = './hubert/hubert_base_ls960_L9_km500.bin'
)

semantic_transformer = SemanticTransformer (
    num_semantic_tokens = wav2vec . codebook_size ,
    dim = 1024 ,
    depth = 6 ,
    flash_attn = True
). cuda ()


trainer = SemanticTransformerTrainer (
    transformer = semantic_transformer ,
    wav2vec = wav2vec ,
    folder = '/path/to/audio/files' ,
    batch_size = 1 ,
    data_max_length = 320 * 32 ,
    num_train_steps = 1
)

trainer . train ()

전. CoarseTransformer

 import torch
from audiolm_pytorch import HubertWithKmeans , SoundStream , CoarseTransformer , CoarseTransformerTrainer

wav2vec = HubertWithKmeans (
    checkpoint_path = './hubert/hubert_base_ls960.pt' ,
    kmeans_path = './hubert/hubert_base_ls960_L9_km500.bin'
)

soundstream = SoundStream . init_and_load_from ( '/path/to/trained/soundstream.pt' )

coarse_transformer = CoarseTransformer (
    num_semantic_tokens = wav2vec . codebook_size ,
    codebook_size = 1024 ,
    num_coarse_quantizers = 3 ,
    dim = 512 ,
    depth = 6 ,
    flash_attn = True
)

trainer = CoarseTransformerTrainer (
    transformer = coarse_transformer ,
    codec = soundstream ,
    wav2vec = wav2vec ,
    folder = '/path/to/audio/files' ,
    batch_size = 1 ,
    data_max_length = 320 * 32 ,
    num_train_steps = 1_000_000
)

trainer . train ()

전. FineTransformer

 import torch
from audiolm_pytorch import SoundStream , FineTransformer , FineTransformerTrainer

soundstream = SoundStream . init_and_load_from ( '/path/to/trained/soundstream.pt' )

fine_transformer = FineTransformer (
    num_coarse_quantizers = 3 ,
    num_fine_quantizers = 5 ,
    codebook_size = 1024 ,
    dim = 512 ,
    depth = 6 ,
    flash_attn = True
)

trainer = FineTransformerTrainer (
    transformer = fine_transformer ,
    codec = soundstream ,
    folder = '/path/to/audio/files' ,
    batch_size = 1 ,
    data_max_length = 320 * 32 ,
    num_train_steps = 1_000_000
)

trainer . train ()

이제 모두 함께

 from audiolm_pytorch import AudioLM

audiolm = AudioLM (
    wav2vec = wav2vec ,
    codec = soundstream ,
    semantic_transformer = semantic_transformer ,
    coarse_transformer = coarse_transformer ,
    fine_transformer = fine_transformer
)

generated_wav = audiolm ( batch_size = 1 )

# or with priming

generated_wav_with_prime = audiolm ( prime_wave = torch . randn ( 1 , 320 * 8 ))

# or with text condition, if given

generated_wav_with_text_condition = audiolm ( text = [ 'chirping of birds and the distant echos of bells' ])

텍스트 조건 오디오 합성

업데이트: 'VALL-E'를 고려하면 이것이 작동할 것 같습니다.

전. 의미 변환기

 import torch
from audiolm_pytorch import HubertWithKmeans , SemanticTransformer , SemanticTransformerTrainer

wav2vec = HubertWithKmeans (
    checkpoint_path = './hubert/hubert_base_ls960.pt' ,
    kmeans_path = './hubert/hubert_base_ls960_L9_km500.bin'
)

semantic_transformer = SemanticTransformer (
    num_semantic_tokens = 500 ,
    dim = 1024 ,
    depth = 6 ,
    has_condition = True ,               # this will have to be set to True
    cond_as_self_attn_prefix = True     # whether to condition as prefix to self attention, instead of cross attention, as was done in 'VALL-E' paper
). cuda ()

# mock text audio dataset (as an example)

# you will have to extend your own from `Dataset`, and return an audio tensor as well as a string (the audio description) in any order (the framework will autodetect and route it into the transformer)

from torch . utils . data import Dataset

class MockTextAudioDataset ( Dataset ):
    def __init__ ( self , length = 100 , audio_length = 320 * 32 ):
        super (). __init__ ()
        self . audio_length = audio_length
        self . len = length

    def __len__ ( self ):
        return self . len

    def __getitem__ ( self , idx ):
        mock_audio = torch . randn ( self . audio_length )
        mock_caption = 'audio caption'
        return mock_caption , mock_audio

dataset = MockTextAudioDataset ()

# instantiate semantic transformer trainer and train

trainer = SemanticTransformerTrainer (
    transformer = semantic_transformer ,
    wav2vec = wav2vec ,
    dataset = dataset ,
    batch_size = 4 ,
    grad_accum_every = 8 ,
    data_max_length = 320 * 32 ,
    num_train_steps = 1_000_000
)

trainer . train ()

# after much training above

sample = trainer . generate ( text = [ 'sound of rain drops on the rooftops' ], batch_size = 1 , max_length = 2 ) # (1, < 128) - may terminate early if it detects [eos]

다중 GPU

모든 트레이너 클래스가 ? Accelerator, accelerate 명령을 사용하면 쉽게 멀티 GPU 훈련을 할 수 있습니다.

프로젝트 루트에서

$ accelerate config

그런 다음 동일한 디렉토리에서

$ accelerate launch train . py

토도

인용

 @inproceedings { Borsos2022AudioLMAL ,
  title  = { AudioLM: a Language Modeling Approach to Audio Generation } ,
  author = { Zal{'a}n Borsos and Rapha{"e}l Marinier and Damien Vincent and Eugene Kharitonov and Olivier Pietquin and Matthew Sharifi and Olivier Teboul and David Grangier and Marco Tagliasacchi and Neil Zeghidour } ,
  year   = { 2022 }
}

 @misc { https://doi.org/10.48550/arxiv.2107.03312 ,
  title  = { SoundStream: An End-to-End Neural Audio Codec } ,
  author = { Zeghidour, Neil and Luebs, Alejandro and Omran, Ahmed and Skoglund, Jan and Tagliasacchi, Marco } ,
  publisher = { arXiv } ,
  url    = { https://arxiv.org/abs/2107.03312 } ,
  year   = { 2021 }
}

 @misc { shazeer2020glu ,
    title   = { GLU Variants Improve Transformer } ,
    author  = { Noam Shazeer } ,
    year    = { 2020 } ,
    url     = { https://arxiv.org/abs/2002.05202 }
}

 @article { Shazeer2019FastTD ,
    title   = { Fast Transformer Decoding: One Write-Head is All You Need } ,
    author  = { Noam M. Shazeer } ,
    journal = { ArXiv } ,
    year    = { 2019 } ,
    volume  = { abs/1911.02150 }
}

 @article { Ho2022ClassifierFreeDG ,
    title   = { Classifier-Free Diffusion Guidance } ,
    author  = { Jonathan Ho } ,
    journal = { ArXiv } ,
    year    = { 2022 } ,
    volume  = { abs/2207.12598 }
}

 @misc { crowson2022 ,
    author  = { Katherine Crowson } ,
    url     = { https://twitter.com/rivershavewings }
}

 @misc { ding2021cogview ,
    title   = { CogView: Mastering Text-to-Image Generation via Transformers } ,
    author  = { Ming Ding and Zhuoyi Yang and Wenyi Hong and Wendi Zheng and Chang Zhou and Da Yin and Junyang Lin and Xu Zou and Zhou Shao and Hongxia Yang and Jie Tang } ,
    year    = { 2021 } ,
    eprint  = { 2105.13290 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CV }
}

 @article { Liu2022FCMFC ,
    title   = { FCM: Forgetful Causal Masking Makes Causal Language Models Better Zero-Shot Learners } ,
    author  = { Hao Liu and Xinyang Geng and Lisa Lee and Igor Mordatch and Sergey Levine and Sharan Narang and P. Abbeel } ,
    journal = { ArXiv } ,
    year    = { 2022 } ,
    volume  = { abs/2210.13432 }
}

 @inproceedings { anonymous2022normformer ,
    title   = { NormFormer: Improved Transformer Pretraining with Extra Normalization } ,
    author  = { Anonymous } ,
    booktitle = { Submitted to The Tenth International Conference on Learning Representations } ,
    year    = { 2022 } ,
    url     = { https://openreview.net/forum?id=GMYWzWztDx5 } ,
    note    = { under review }
}

 @misc { liu2021swin ,
    title   = { Swin Transformer V2: Scaling Up Capacity and Resolution } ,
    author  = { Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo } ,
    year    = { 2021 } ,
    eprint  = { 2111.09883 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CV }
}

 @article { Li2021LocalViTBL ,
    title   = { LocalViT: Bringing Locality to Vision Transformers } ,
    author  = { Yawei Li and K. Zhang and Jie Cao and Radu Timofte and Luc Van Gool } ,
    journal = { ArXiv } ,
    year    = { 2021 } ,
    volume  = { abs/2104.05707 }
}

 @article { Defossez2022HighFN ,
    title   = { High Fidelity Neural Audio Compression } ,
    author  = { Alexandre D'efossez and Jade Copet and Gabriel Synnaeve and Yossi Adi } ,
    journal = { ArXiv } ,
    year    = { 2022 } ,
    volume  = { abs/2210.13438 }
}

 @article { Hu2017SqueezeandExcitationN ,
    title   = { Squeeze-and-Excitation Networks } ,
    author  = { Jie Hu and Li Shen and Gang Sun } ,
    journal = { 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition } ,
    year    = { 2017 } ,
    pages   = { 7132-7141 }
}

 @inproceedings { Yang2023HiFiCodecGV ,
    title   = { HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec } ,
    author  = { Dongchao Yang and Songxiang Liu and Rongjie Huang and Jinchuan Tian and Chao Weng and Yuexian Zou } ,
    year    = { 2023 }
}

 @article { Kazemnejad2023TheIO ,
    title   = { The Impact of Positional Encoding on Length Generalization in Transformers } ,
    author  = { Amirhossein Kazemnejad and Inkit Padhi and Karthikeyan Natesan Ramamurthy and Payel Das and Siva Reddy } ,
    journal = { ArXiv } ,
    year    = { 2023 } ,
    volume  = { abs/2305.19466 }
}

 @inproceedings { dao2022flashattention ,
    title   = { Flash{A}ttention: Fast and Memory-Efficient Exact Attention with {IO}-Awareness } ,
    author  = { Dao, Tri and Fu, Daniel Y. and Ermon, Stefano and Rudra, Atri and R{'e}, Christopher } ,
    booktitle = { Advances in Neural Information Processing Systems } ,
    year    = { 2022 }
}

 @misc { yu2023language ,
    title   = { Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation } ,
    author  = { Lijun Yu and José Lezama and Nitesh B. Gundavarapu and Luca Versari and Kihyuk Sohn and David Minnen and Yong Cheng and Agrim Gupta and Xiuye Gu and Alexander G. Hauptmann and Boqing Gong and Ming-Hsuan Yang and Irfan Essa and David A. Ross and Lu Jiang } ,
    year    = { 2023 } ,
    eprint  = { 2310.05737 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CV }
}

 @inproceedings { Katsch2023GateLoopFD ,
    title   = { GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling } ,
    author  = { Tobias Katsch } ,
    year    = { 2023 } ,
    url     = { https://api.semanticscholar.org/CorpusID:265018962 }
}

 @article { Fifty2024Restructuring ,
    title   = { Restructuring Vector Quantization with the Rotation Trick } ,
    author  = { Christopher Fifty, Ronald G. Junkins, Dennis Duan, Aniketh Iyengar, Jerry W. Liu, Ehsan Amid, Sebastian Thrun, Christopher Ré } ,
    journal = { ArXiv } ,
    year    = { 2024 } ,
    volume  = { abs/2410.06424 } ,
    url     = { https://api.semanticscholar.org/CorpusID:273229218 }
}

 @inproceedings { Zhou2024ValueRL ,
    title   = { Value Residual Learning For Alleviating Attention Concentration In Transformers } ,
    author  = { Zhanchao Zhou and Tianyi Wu and Zhiyun Jiang and Zhenzhong Lan } ,
    year    = { 2024 } ,
    url     = { https://api.semanticscholar.org/CorpusID:273532030 }
}