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.
Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.
| Date | Stars |
|---|---|
| 2026-07-24 | 409 |
| 2026-07-25 | 409 |
| 2026-07-28 | 409 |
| 2026-07-30 | 409 |
| 2026-08-06 | 409 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
 # WaveGrad Implementation (PyTorch) of Google Brain's high-fidelity WaveGrad vocoder ([paper](https://arxiv.org/pdf/2009.00713.pdf)). First implementation on GitHub with high-quality generation for 6-iterations. ## **Status** - [x] Documented API. - [x] High-fidelity generation. - [x] Multi-iteration inference support (**stable for low iterations**). - [x] Stable and fast training with **mixed-precision** support. - [x] **Distributed training** support. - [x] Training also successfully runs on a single 12GB GPU with batch size 96. - [x] CLI inference support. - [x] Flexible architecture configuration for your own data. - [x] Estimated RTF on popular GPU and CPU devices (see below). - [x] 100- and lower-iteration inferences are faster than real-time on RTX 2080 Ti. **6-iteration inference is faster than one reported in the paper**. - [x] **Parallel grid search for the best noise schedule**. - [x] Uploaded generated samples for different number of iterations (see `generated_samples` folder). - [x] [Pretrained checkpoint](https://drive.google.com/file/d/1X_AquK11C0j7U1lLxMDBdK5guabHaoXB/view?usp=sharing) on 22KHz LJSpeech dataset **with noise schedules**. #### Real-time factor (RTF) **Number of parameters**: 15.810.401 | Model | Stable | RTX 2080 Ti | Tesla K80 | Intel Xeon 2.3GHz* | |-------------------|-----------|---------------|---------------|--------------------| | 1000 iterations | **+** | 9.59 | - | - | | 100 iterations | **+** | 0.94 | 5.85 | - | | 50 iterations | **+** | 0.45 | 2.92 | - | | 25 iterations | **+** | 0.22 | 1.45 | - | | 12 iterations | **+** | 0.10 | 0.69 | 4.55 | | 6 iterations | **+** | 0.04 | 0.33 | 2.09 | ***Note**: Used an old version of Intel Xeon CPU. ___ ## About WaveGrad is a conditional model for waveform generation through estimating gradients of the data density with WaveNet-similar sampling quality. **This vocoder is neither GAN, nor Normalizing Flow, nor classical autoregressive model**. The main concept of vocoder is based on *Denoising Diffusion Probabilistic Models* (DDPM), which utilize *Langevin dynamics* and *score matching* frameworks. Furthemore, comparing to classic DDPM, WaveGrad achieves super-fast convergence (6 iterations and probably lower) w.r.t. Langevin dynamics iterative sampling scheme. ___ ## Installation 1. Clone this repo: ```bash git clone https://github.com/ivanvovk/WaveGrad.git cd WaveGrad ``` 2. Install requirements: ```bash pip install -r requirements.txt ``` ___ ## Training #### 1 Preparing data 1. Make train and test filelists of your audio data like ones included into `filelists` folder. 2. Make a configuration file* in `configs` folder. ***Note:** if you are going to change `hop_length` for STFT, then make sure that the product of your upsampling `factors` in config is equal to your new `hop_length`. #### 2 Single and Distributed GPU training 1. Open `runs/train.sh` script and specify visible GPU devices and path to your configuration file. If you specify more than one GPU the training will run in distributed mode. 2. Run `sh runs/train.sh` #### 3 Tensorboard and logging To track your training process run tensorboard by `tensorboard --logdir=logs/YOUR_LOGDIR_FOLDER`. All logging information and checkpoints will be stored in `logs/YOUR_LOGDIR_FOLDER`. `logdir` is specified in config file. #### 4 Noise schedule grid search Once model is trained, grid search for the best schedule* for a needed number of iterations in [`notebooks/inference.ipynb`](notebooks/inference.ipynb). The code supports parallelism, so you can specify more than one number of jobs to accelerate the search. ***Note**: grid search is necessary ju
Excerpt of 8,723 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7afed6f0b4228867, topic:text-to-speech, topic:tts, topic:speech-synthesis