spear tts pytorch

Spear-TTS - Pytorch

在 Pytorch 實現 Spear-TTS - 多說話者文字轉語音注意網絡

這裡建構的文本到語義模組將用於 SoundStorm 進行調節。

欣賞

• 他們慷慨的贊助工作和開源尖端人工智慧研究的穩定性

• Lucas Newman 完成了反向翻譯部分以及波束搜尋解碼！

• Lucas Newman 完成了最終文字到語意轉換器的訓練程式碼！

安裝

$ 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

• 新增 eos 邏輯 + 生成，並在 soundstorm 中連接端對端生成

• 加入第一個預訓練語音到語音，重建 60% 已刪除的標記

• 由於資源匱乏，為此計畫增加輟學者

• 增加訓練期間凍結編碼器/解碼器層的整體靈活性

• 新增小語音訓練步驟 -> 文字語料庫並產生偽標記資料集 + 微調（感謝@lucasnewman）

• 新增對文字 -> 語音 + 偽標籤資料集進行微調的最後一步

• 找出儲存和管理偽標籤生成資料集的最佳方法

• 批次波束搜尋解碼

• 允許在解碼器中使用旋轉位置+閃光注意，給Tri另一個引用

• 將推測性解碼與一些即興創作相結合 - 使用早期退出策略在同一模型中完成

• 為 starter + 單一/分組鍵值新增快取的鍵/值，確保在 Flash Attention 2 進入 pytorch 核心之前 Flash Attention 可以支援專門的因果掩碼

• 完善音訊文字產生工作流程

• 將真實的音訊文字資料集與產生的資料集連接起來 -> 或能夠將真實的音訊文字資料集轉換為產生的資料集

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 }
}