e2 tts mlx下載e2 tts mlx源代碼下載

e2 tts mlx

Ai源碼

v0.0.6

下載

E2 TTS圖

E2 TTS - MLX

通過MLX框架，實施E2-TT，令人尷尬的完全非自動迴旋零射擊TT。

E2 TTS是一種非自動回形的，零射擊的文本對語音系統，通過使用在掩蓋的音頻填充任務上訓練的流量匹配MEL Spectrogram生成器，簡化了典型的TTS管道，而無需幀級對齊信息。

該實現基於Pytorch中的Lucidrains實現，該實現與論文不同，因為它使用多式變壓器用於文本和音頻，並且進行條件完成了每個變壓器塊。

安裝

pip install mlx-e2-tts

用法

 import mlx . core as mx

from e2_tts_mlx . model import E2TTS
from e2_tts_mlx . trainer import E2Trainer
from e2_tts_mlx . data import load_libritts_r

e2tts = E2TTS (
    tokenizer = "char-utf8" ,  # or "phoneme_en" / callable
    cond_drop_prob = 0.25 ,
    frac_lengths_mask = ( 0.7 , 0.9 ),
    transformer = dict (
        dim = 1024 ,
        depth = 24 ,
        heads = 16 ,
        text_depth = 12 ,
        text_heads = 8 ,
        max_seq_len = 4096 ,
        dropout = 0.1
    )
)
mx . eval ( e2tts . parameters ())

batch_size = 32

dataset = load_libritts_r ( split = "dev-clean" )  # or any audio/caption dataset

trainer = E2Trainer ( model = e2tts , num_warmup_steps = 20_000 )

trainer . train (
    train_dataset = dataset ,
    learning_rate = 7.5e-5 ,
    batch_size = batch_size ,
    total_steps = 1_000_000
)

...經過大量培訓...

 generated_audio = e2tts . sample (
    cond = cond ,  # reference mel spectrogram for voice matching
    text = text ,  # caption for generation
    duration = duration , # from a trained DurationPredictor or otherwise
    steps = 32 ,
    cfg_strength = 1.0 ,  # if trained for cfg
    use_vocos = True  # set to False to get mel spectrograms instead of audio
)

有關單個設備培訓的示例，請參見train_example.py 。

欣賞

Lucidrains在Pytorch中的原始實現。

引用

 @inproceedings { Eskimez2024E2TE ,
    title   = { E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS } ,
    author  = { Sefik Emre Eskimez and Xiaofei Wang and Manthan Thakker and Canrun Li and Chung-Hsien Tsai and Zhen Xiao and Hemin Yang and Zirun Zhu and Min Tang and Xu Tan and Yanqing Liu and Sheng Zhao and Naoyuki Kanda } ,
    year    = { 2024 } ,
    url     = { https://api.semanticscholar.org/CorpusID:270738197 }
}

 @article { Burtsev2021MultiStreamT ,
    title     = { Multi-Stream Transformers } ,
    author    = { Mikhail S. Burtsev and Anna Rumshisky } ,
    journal   = { ArXiv } ,
    year      = { 2021 } ,
    volume    = { abs/2107.10342 } ,
    url       = { https://api.semanticscholar.org/CorpusID:236171087 }
}