The Open Source Code of UniAudio

🔊 Text-Prompted Generative Audio Model

A collection of resources and papers on Diffusion Models

Text Normalization & Inverse Text Normalization

Muzic: Music Understanding and Generation with Artificial Intelligence

A light-weight Python library for computing Kaldi-style acoustic features based on NumPy

List of speech synthesis papers.

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

The dataset of Speech Recognition

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

A TensorFlow implementation of DeepMind's WaveNet paper

A clone of Darts (Double-ARray Trie System)

A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

DeepMind's Tacotron-2 Tensorflow implementation

This is now the official location of the Merlin project.

Blind Source Separation for Audio Recognition Tasks

Chinese keras documents with more examples, explanations and tips.