diffwave
mlp-singer
Our great sponsors
| diffwave | mlp-singer | |
|---|---|---|
| 3 | 2 | |
| 724 | 113 | |
| 2.5% | 0.0% | |
| 1.5 | 0.0 | |
| about 1 month ago | about 2 years ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
diffwave
-
AI Speech to Voice morphing
glad someone else is interested thanks for that repo. what's the link to the tut? Im not too familiar with deep learning but im down to colab. I also asked around on ycombinator and was referred to this repo https://github.com/lmnt-com/diffwave.
- AI Speech to Voice Morphing
-
Interesting research areas in Digital Signal Processing.
Here’s another one
mlp-singer
-
Can you recommend any music created by AI and not by humans?
Check out Google Magenta, they have some pretty cool demos. Also checkout MLP Singer (disclaimer: I'm the first author), where we used a stack of multi-layer perceptrons to build an AI model that sings given lyrics text and a MIDI file. Hope this helps!
-
MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis
Paper: https://arxiv.org/abs/2106.07886 \ Demo: https://mlpsinger.github.io \ Code: https://github.com/neosapience/mlp-singer
What are some alternatives?
hifi-gan - HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
WaveRNN - WaveRNN Vocoder + TTS
TensorFlowTTS - :stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
wavegrad - A fast, high-quality neural vocoder.
nnsvs - Neural network-based singing voice synthesis library for research
aeneas - aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
tts-generation-webui - TTS Generation Web UI (Bark, MusicGen + AudioGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, MAGNet, StyleTTS2, MMS)
allosaurus - Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production