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.
WaveNet vocoder
| Date | Stars |
|---|---|
| 2026-07-24 | 2375 |
| 2026-07-25 | 2375 |
| 2026-07-28 | 2375 |
| 2026-07-30 | 2375 |
| 2026-08-06 | 2375 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# WaveNet vocoder [](https://pypi.python.org/pypi/wavenet_vocoder) [](https://travis-ci.org/r9y9/wavenet_vocoder) [](https://ci.appveyor.com/project/r9y9/wavenet-vocoder) [](https://zenodo.org/badge/latestdoi/115492234) **NOTE**: This is the development version. If you need a stable version, please checkout the v0.1.1. The goal of the repository is to provide an implementation of the WaveNet vocoder, which can generate high quality raw speech samples conditioned on linguistic or acoustic features. Audio samples are available at https://r9y9.github.io/wavenet_vocoder/. ## News - 2019/10/31: The repository has been adapted to [ESPnet](https://github.com/espnet/espnet). English, Chinese, and Japanese samples and pretrained models are available there. See https://github.com/espnet/espnet and https://github.com/espnet/espnet#tts-results for details. ## Online TTS demo A notebook supposed to be executed on https://colab.research.google.com is available: - [Tacotron2: WaveNet-based text-to-speech demo](https://colab.research.google.com/github/r9y9/Colaboratory/blob/master/Tacotron2_and_WaveNet_text_to_speech_demo.ipynb) ## Highlights - Focus on local and global conditioning of WaveNet, which is essential for vocoder. - 16-bit raw audio modeling by mixture distributions: mixture of logistics (MoL), mixture of Gaussians, and single Gaussian distributions are supported. - Various audio samples and pre-trained models - Fast inference by caching intermediate states in convolutions. Similar to [arXiv:1611.09482](https://arxiv.org/abs/1611.09482) - Integration with ESPNet (https://github.com/espnet/espnet) ## Pre-trained models **Note**: This is not itself a text-to-speech (TTS) model. With a pre-trained model provided here, you can synthesize waveform given a *mel spectrogram*, not raw text. You will need mel-spectrogram prediction model (such as Tacotron2) to use the pre-trained models for TTS. **Note**: As for the pretrained model for LJSpeech, the model was fine-tuned multiple times and trained for more than 1000k steps in total. Please refer to the issues ([#1](https://github.com/r9y9/wavenet_vocoder/issues/1#issuecomment-361130247), [#75](https://github.com/r9y9/wavenet_vocoder/issues/75), [#45](https://github.com/r9y9/wavenet_vocoder/issues/45#issuecomment-383313651)) to know how the model was trained. | Model URL | Data | Hyper params URL | Git commit | Steps | |----------------------------------------------------------------------------------------------------------------------------------|------------|------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------|---------------| | [link](https://www.dropbox.com/s/zdbfprugbagfp2w/20180510_mixture_lj_checkpoint_step000320000_ema.pth?dl=0) | LJSpeech | [link](https://www.dropbox.com/s/0vsd7973w20eskz/20180510_mixture_lj_checkpoint_step000320000_ema.json?dl=0) | [2092a64](https://github.com/r9y9/wavenet_vocoder/commit/2092a647e60ce002389818de1fa66d0a2c5763d8) | 1000k~ steps | | [link](https://www.dropbox.com/s/d0qk4ow9uuh2lww/20180212_mixture_multispeaker_cmu_arctic_checkpoint_step000740000_ema.pth?dl=0) | CMU ARCTIC | [link](https://www.dropbox.com/s/i35yigj5hvmeol8/20180212_multispeaker_cmu_arctic_mixture.json?dl=0) | [b1a1076](h
Excerpt of 13,013 characters
Read on GitHub
Ryuichi Yamamoto · @line · Japan
245
4
3
1
1
1
1
Cbrom
1
1
1
Yunchao He · China
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c735998781c63eef, topic:speech-synthesis, readme:text-to-speech
matched fp:c735998781c63eef, topic:pytorch