spear tts pytorch

Spear-TTS - Pytorch

在 Pytorch 中实现 Spear-TTS - 多说话者文本转语音注意网络

这里构建的文本到语义模块将用于 SoundStorm 进行调节。

欣赏

• 他们慷慨的赞助工作和开源尖端人工智能研究的稳定性

• Lucas Newman 完成了反向翻译部分以及波束搜索解码！

• Lucas Newman 完成了最终文本到语义转换器的训练代码！

安装

$ pip install spear-tts-pytorch

用法

 import torch

from audiolm_pytorch import HubertWithKmeans

from spear_tts_pytorch import (
    TextToSemantic ,
    SemanticToTextDatasetGenerator ,
    GeneratedAudioTextDataset ,
    MockDataset
)

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

model = TextToSemantic (
    wav2vec = wav2vec ,
    dim = 512 ,
    num_text_token_ids = 256 ,
    heads = 8 ,
    target_kv_heads = 2 , # grouped query attention, for memory efficient decoding
    source_depth = 1 ,
    target_depth = 1
)

ds = MockDataset ( 10 )

dataset_generator = SemanticToTextDatasetGenerator (
    model = model ,
    dataset = ds ,
    folder = './output_folder'
)

dataset_generator ( max_length = 2 )

generated_dataset = GeneratedAudioTextDataset (
    folder = './output_folder'
)

assert len ( generated_dataset ) == 10 

托多

• 添加 eos 逻辑 + 生成，并在 soundstorm 中连接端到端生成

• 添加第一个预训练语音到语音，重建 60% 已删除的标记

• 由于资源匮乏，为此项目添加辍学者

• 增加训练期间冻结编码器/解码器层的总体灵活性

• 添加小语音训练步骤 -> 文本语料库并生成伪标记数据集 + 微调（感谢@lucasnewman）

• 添加对文本 -> 语音 + 伪标签数据集进行微调的最后一步

• 找出存储和管理伪标签生成数据集的最佳方法

• 批量波束搜索解码

• 允许在解码器中使用旋转位置+闪光注意，给Tri另一个引用

• 将推测性解码与一些即兴创作相结合 - 使用早期退出策略在同一模型中完成

• 为 starter + 单个/分组键​​值添加缓存的键/值，确保在 Flash Attention 2 进入 pytorch 核心之前 Flash Attention 可以支持专门的因果掩码

• 完善音频文本生成工作流程

• 将真实的音频文本数据集与生成的数据集连接起来 -> 或者能够将真实的音频文本数据集转换为生成的数据集

引文

 @misc { kharitonov2023speak ,
    title   = { Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision } , 
    author  = { Eugene Kharitonov and Damien Vincent and Zalán Borsos and Raphaël Marinier and Sertan Girgin and Olivier Pietquin and Matt Sharifi and Marco Tagliasacchi and Neil Zeghidour } ,
    year    = { 2023 } ,
    eprint  = { 2302.03540 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.SD }
}

 @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 { shi2023enhance ,
    title   = { Enhance audio generation controllability through representation similarity regularization } , 
    author  = { Yangyang Shi and Gael Le Lan and Varun Nagaraja and Zhaoheng Ni and Xinhao Mei and Ernie Chang and Forrest Iandola and Yang Liu and Vikas Chandra } ,
    year    = { 2023 } ,
    eprint  = { 2309.08773 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.SD }
}

 @article { Ainslie2023GQATG ,
    title   = { GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints } ,
    author  = { Joshua Ainslie and James Lee-Thorp and Michiel de Jong and Yury Zemlyanskiy and Federico Lebr'on and Sumit K. Sanghai } ,
    journal = { ArXiv } ,
    year    = { 2023 } ,
    volume  = { abs/2305.13245 } ,
    url     = { https://api.semanticscholar.org/CorpusID:258833177 }
}

 @inproceedings { Leviathan2022FastIF ,
    title   = { Fast Inference from Transformers via Speculative Decoding } ,
    author  = { Yaniv Leviathan and Matan Kalman and Y. Matias } ,
    booktitle = { International Conference on Machine Learning } ,
    year    = { 2022 } ,
    url     = { https://api.semanticscholar.org/CorpusID:254096365 }
}