Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
unofficial vits2-TTS implementation in pytorch
| Date | Stars |
|---|---|
| 2026-07-24 | 548 |
| 2026-07-25 | 548 |
| 2026-07-28 | 548 |
| 2026-07-30 | 548 |
| 2026-08-06 | 548 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
### Jungil Kong, Jihoon Park, Beomjeong Kim, Jeongmin Kim, Dohee Kong, Sangjin Kim
Unofficial implementation of the [VITS2 paper](https://arxiv.org/abs/2307.16430), sequel to [VITS paper](https://arxiv.org/abs/2106.06103). (thanks to the authors for their work!)
Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms of its intermittent unnaturalness, computational efficiency, and strong dependence on phoneme conversion. In this work, we introduce VITS2, a single-stage text-to-speech model that efficiently synthesizes a more natural speech by improving several aspects of the previous work. We propose improved structures and training mechanisms and present that the proposed methods are effective in improving naturalness, similarity of speech characteristics in a multi-speaker model, and efficiency of training and inference. Furthermore, we demonstrate that the strong dependence on phoneme conversion in previous works can be significantly reduced with our method, which allows a fully end-toend single-stage approach.
## Credits
- We will build this repo based on the [VITS repo](https://github.com/jaywalnut310/vits). The goal is to make this model easier to transfer learning from VITS pretrained model!
- (08-17-2023) - The authors were really kind to guide me through the paper and answer my questions. I am open to discuss any changes or answer questions regarding the implementation. Please feel free to open an issue or contact me directly.
# Pretrained checkpoints
- [LJSpeech-no-sdp](https://drive.google.com/drive/folders/1U-1EqBMXqmEqK0aUhbCJOquowbvKkLmc?usp=sharing) (refer to config.yaml in this checkppoint folder) | 64k steps | proof that training works!
Would recommend experts to rename the ckpts to *_0.pth and starting the training using transfer learning. (I will add a notebook for this soon to help beginers).
- [x] Check 'Discussion' page for training logs and tensorboard links and other community contributions.
# Sample audio
- Russian trained model samples [#32](https://github.com/p0p4k/vits2_pytorch/discussions/32). Thanks to [@shigabeev](https://github.com/shigabeev) for sharing the samples.
- Some samples on non-native EN dataset [discussion page](https://github.com/p0p4k/vits2_pytorch/discussions/18). Thanks to [@athenasaurav](https://github.com/athenasaurav) for using his private GPU resources and dataset!
- Added sample audio @104k steps. [ljspeech-nosdp](resources/test.wav) ; [tensorboard](https://github.com/p0p4k/vits2_pytorch/discussions/12)
- [vietnamese samples](https://github.com/p0p4k/vits2_pytorch/pull/10#issuecomment-1682307529) Thanks to [@ductho9799](https://github.com/ductho9799) for sharing!
## Prerequisites
1. Python >= 3.10
2. Tested on Pytorch version 1.13.1 with Google Colab and LambdaLabs cloud.
3. Clone this repository
4. Install python requirements. Please refer [requirements.txt](requirements.txt)
1. You may need to install espeak first: `apt-get install espeak`
5. 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`
1. 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`
6. Build Monotonic Alignment Search and run preprocessing if you use your own datasets.
```sh
# 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.
# pythExcerpt of 9,273 characters
Read on GitHub
p0p
114
14
4
3
3
Kevin Wang
2
2
2
1
1
1
Alexander Haus
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:49fec8a5e875ac79, topic:text-to-speech, topic:tts, readme:text-to-speech
matched fp:49fec8a5e875ac79, topic:deep-learning, topic:pytorch