Component library and custom registry built on top of shadcn/ui
Python Audio Analysis Library: Feature Extraction, Classification
SOTA discrete acoustic codec models with 40/75 tokens per second
An Open Source text-to-speech system built by inverting Whisper
Unofficial Parallel WaveGAN
Singing Voice Synthesis via Shallow Diffusion Mechanism
WaveRNN Vocoder + TTS
Real-Time State-of-the-art Speech Synthesis for Tensorflow 2
Conditional Variational Autoencoder with Adversarial Learning
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)
Generative Adversarial Networks for Efficient and High Fidelity Speech
DeepMind's Tacotron-2 Tensorflow implementation
TensorFlow Implementation of DC-TTS: yet another text-to-speech model