torchview: visualize pytorch models

Collection of audio-focused loss functions in PyTorch

speacher is a speech teacher framework that enables research in curriculum learning for speech recognition and quality assessment for speech synthesis models.

A multi-voice TTS system trained with an emphasis on quality

PyTorch reimplementation of "Keyword Transformer: A Self-Attention Model for Keyword Spotting"

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

Public domain corpus of Catalan text

Pytorch!!!Pytorch!!!Pytorch!!! Dynamic Convolution: Attention over Convolution Kernels (CVPR-2020)

A library for efficient similarity search and clustering of dense vectors.

Vector (and Scalar) Quantization, in Pytorch

Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch

"Deep Generative Modeling": Introductory Examples

😎 A curated list of awesome GitHub Profile which updates in real time

A PyTorch-based Speech Toolkit

Collecting research materials on EBM/EBL (Energy Based Models, Energy Based Learning)

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

A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

A PyTorch implementation of Tacotron2, an end-to-end text-to-speech(TTS) system described in "Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions".

A pytorch implementation of a Text-to-Speech system based on NVIDIA's Tacotron2 text2mel plus a neural vocoder

This is our work on learning speaking style in speech synthesis but only using the pitch frequency sub-band as a speaker reference. We trained a modified version of the NVIDIA's Tacotron2 model but…

A NVIDIA's Pytorch Tacotron2 adaptation with unsupervised Global Style Tokens. Instead of using the whole mel-scale spectrogram representation in the GST input, we extracted and used only the pitch…

A NVIDIA's Pytorch Tacotron2 adaptation with unsupervised Global Style Tokens. The model has been trained with the English read-speech LJSpeech Dataset.

Self-Supervised Speech Pre-training and Representation Learning Toolkit

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.