Markus Toman

Slightly alternative material collection for building reliable agents

2018/2019 TTS framework integrating state of the art open source methods

Frontend system for HMM-based speech synthesis models generated by HTS.

NeMo: a toolkit for conversational AI

Build resilient language agents as graphs.

An efficient video loader for deep learning with smart shuffling that's super easy to digest

Deep learning for Text to Speech

Unofficial PyTorch implementation of MelGAN vocoder (Training in progress)

A Flow-based Generative Network for Speech Synthesis

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

Twelve days of XMas in twelve languages

Fatcord's Alternative WaveRNN (Faster training)

A PyTorch implementation of "Robust Universal Neural Vocoding"

Pytorch implementation of Deepmind's WaveRNN model

Teaching material Markov Models

Reference implementation of real-time autoregressive wavenet inference

Microtrans Games Inc. presents Ryskim

DeepMind's Tacotron-2 Tensorflow implementation

TTS (Tacotron + WaveRNN)

e-contaminated Gausssian distribution loss for Keras with Tensorflow backend

vim linux settings

No description provided.

Some results from research project "Acoustic modeling and transformation of varieties for speech synthesis"

WaveNet vocoder

This is now the official location of the Merlin project.

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.

gvim windows settings

German audio-only games using TTS

Mycroft's TTS engine, based on CMU's Flite (Festival Lite)