romans01's repositories
test-analytics
Automatically exported from code.google.com/p/test-analytics
ChatGPT2
Reverse engineered ChatGPT API. Uses official model same as the website.
classy-sort-yolov5
Simple and adaptable multi-object tracker that works for any object category. YOLOv5 + SORT implementation.
Kerberos.NET
A Managed Code validator for Kerberos tickets
lit-gptr1
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
nanoGPTr1
The simplest, fastest repository for training/finetuning medium-sized GPTs.
pytorch-cifar
95.16% on CIFAR10 with PyTorch
Voice-synthesis
This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.