本repo包含了我用于训练原神VITS模型对源代码做出的修改，以及新的config文件。

由于各种原因，模型和数据集暂无法公布，感兴趣可以自行提取，自行训练。

此外，也可以尝试使用公开的api：https://233366.proxy.nscc-gz.cn:8888/ 来进行尝试，请注意此模型禁止用于任何商业用途。请注意多次生成的效果不会一致，可以多次尝试来选择一次较好的效果。

支持的说话者： ['派蒙', '凯亚', '安柏', '丽莎', '琴', '香菱', '枫原万叶', '迪卢克', '温迪', '可莉', '早柚', '托马', '芭芭拉', '优菈', '云堇', '钟离', '魈', '凝光', '雷电将军', '北斗', '甘雨', '七七', '刻晴', '神里绫华', '戴因斯雷布', '雷泽', '神里绫人', '罗莎莉亚', '阿贝多', '八重神子', '宵宫', '荒泷一斗', '九条裟罗', '夜兰', '珊瑚宫心海', '五郎', '散兵', '女士', '达达利亚', '莫娜', '班尼特', '申鹤', '行秋', '烟绯', '久岐忍', '辛焱', '砂糖', '胡桃', '重云', '菲谢尔', '诺艾尔', '迪奥娜', '鹿野院平藏']

Query String 参数：

示例：https://233366.proxy.nscc-gz.cn:8888/?text=你好&speaker=派蒙

In our recent paper, we propose VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech.

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.

Visit our demo for audio samples.

We also provide the pretrained models.

** Update note: Thanks to Rishikesh (ऋषिकेश), our interactive TTS demo is now available on Colab Notebook.

VITS at training	VITS at inference

0. Python >= 3.6
1. Clone this repository
2. Install python requirements. Please refer requirements.txt
   1. You may need to install espeak first: apt-get install espeak
3. Download datasets
   1. Download and extract the LJ Speech dataset, then rename or create a link to the dataset folder: ln -s /path/to/LJSpeech-1.1/wavs DUMMY1
   2. For mult-speaker setting, download and extract the VCTK dataset, and downsample wav files to 22050 Hz. Then rename or create a link to the dataset folder: ln -s /path/to/VCTK-Corpus/downsampled_wavs DUMMY2
4. Build Monotonic Alignment Search and run preprocessing if you use your own datasets.

# Cython-version Monotonoic Alignment Search
cd monotonic_align
python setup.py build_ext --inplace

# Preprocessing (g2p) for your own datasets. Preprocessed phonemes for LJ Speech and VCTK have been already provided.
# python preprocess.py --text_index 1 --filelists filelists/ljs_audio_text_train_filelist.txt filelists/ljs_audio_text_val_filelist.txt filelists/ljs_audio_text_test_filelist.txt 
# python preprocess.py --text_index 2 --filelists filelists/vctk_audio_sid_text_train_filelist.txt filelists/vctk_audio_sid_text_val_filelist.txt filelists/vctk_audio_sid_text_test_filelist.txt

# LJ Speech
python train.py -c configs/ljs_base.json -m ljs_base

# VCTK
python train_ms.py -c configs/vctk_base.json -m vctk_base

See inference.ipynb