Pinned Repositories
multiwoz
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
Aargh
Blizzard2013_Segmentation
Transcripts and segmentation for the Blizzard 2013 audiobooks also known as the Lessac or Blizzard 2013 dataset.
Face_Cleaner
Automated trimming and cleaning of 3D facial scans
Multilingual_Text_to_Speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
MultiWOZ_Evaluation
Unified MultiWOZ evaluation scripts for the context-to-response task.
Star_Tracker
Arduino DIY telescope GoTo for arbitrary mounts.
Toom_Rendering_Engine
Partial remake of the original Doom 1. Written as an assignment during a programming course. Uses doom-like rendering.
Unity_Tower_Defence
Classical top-down tower defence made in Unity 3D game engine.
WaveRNN
WaveRNN Vocoder + TTS
Tomiinek's Repositories
Tomiinek/Multilingual_Text_to_Speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
Tomiinek/MultiWOZ_Evaluation
Unified MultiWOZ evaluation scripts for the context-to-response task.
Tomiinek/Star_Tracker
Arduino DIY telescope GoTo for arbitrary mounts.
Tomiinek/Blizzard2013_Segmentation
Transcripts and segmentation for the Blizzard 2013 audiobooks also known as the Lessac or Blizzard 2013 dataset.
Tomiinek/Aargh
Tomiinek/WaveRNN
WaveRNN Vocoder + TTS
Tomiinek/Unity_Tower_Defence
Classical top-down tower defence made in Unity 3D game engine.
Tomiinek/Face_Cleaner
Automated trimming and cleaning of 3D facial scans
Tomiinek/Toom_Rendering_Engine
Partial remake of the original Doom 1. Written as an assignment during a programming course. Uses doom-like rendering.
Tomiinek/npfl114
Materials for the Deep Learning -- ÚFAL course NPFL114
Tomiinek/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.
Tomiinek/Sequicity_Knowledge_Base
Implementation of knowledge base for the sequicity model.
Tomiinek/tomiinek.github.io
Tomiinek/UE4_Endless_Racer
Endless racer (runner) created using Blueprints Visual Scripting system of the Unreal Engine 4.
Tomiinek/WaveRNN-Pytorch
Fatcord's Alternative WaveRNN (Faster training)
Tomiinek/ai-audio-startups
Community list of startups working with AI in audio and music technology
Tomiinek/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Tomiinek/k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
Tomiinek/lhotse
Tools for handling speech data in machine learning projects.
Tomiinek/multiwoz
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
Tomiinek/Phaser3_Space_Shooter
A simple 2D shooter exploiting features of the Phaser 3 framework.
Tomiinek/pyreaper
A python wrapper for REAPER
Tomiinek/REAPER
C-interface for REAPER (see cwrap/ for details)
Tomiinek/silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
Tomiinek/spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
Tomiinek/text
Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.
Tomiinek/TorchPQ
Efficient implementations of Product Quantization and its variants using Pytorch and CUDA
Tomiinek/TSP_Kiwi
Tomiinek/tts-scores
Scripts for computing the Intelligibility and CLVP scores for evaluating TTS models
Tomiinek/WavTokenizer
SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling