Tomáš Nekvinda's repositories
Multilingual_Text_to_Speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
Star_Tracker
Arduino DIY telescope GoTo for arbitrary mounts.
MultiWOZ_Evaluation
Unified MultiWOZ evaluation scripts for the context-to-response task.
Blizzard2013_Segmentation
Transcripts and segmentation for the Blizzard 2013 audiobooks also known as the Lessac or Blizzard 2013 dataset.
Unity_Tower_Defence
Classical top-down tower defence made in Unity 3D game engine.
Face_Cleaner
Automated trimming and cleaning of 3D facial scans
Toom_Rendering_Engine
Partial remake of the original Doom 1. Written as an assignment during a programming course. Uses doom-like rendering.
Pascal_Star_Fighter
A simple Star Fighter game which I created as a final assignment in the introductory course of programming during the first semester at the uni.
Sequicity_Knowledge_Base
Implementation of knowledge base for the sequicity model.
UE4_Endless_Racer
Endless racer (runner) created using Blueprints Visual Scripting system of the Unreal Engine 4.
WaveRNN-Pytorch
Fatcord's Alternative WaveRNN (Faster training)
ai-audio-startups
Community list of startups working with AI in audio and music technology
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
lhotse
Tools for handling speech data in machine learning projects.
multiwoz
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
Phaser3_Space_Shooter
A simple 2D shooter exploiting features of the Phaser 3 framework.
pyreaper
A python wrapper for REAPER
REAPER
C-interface for REAPER (see cwrap/ for details)
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
text
Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.
TorchPQ
Efficient implementations of Product Quantization and its variants using Pytorch and CUDA
tts-scores
Scripts for computing the Intelligibility and CLVP scores for evaluating TTS models
WavTokenizer
SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling