owos

lingua

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

picky_bpe

BPE modification that implements removing of the intermediate tokens during tokenizer training.

ml-starter-kit

This repo contains code to start a new ml project

spell-checkers-comparison

Comparison of existing spell checking tools

whisper-finetune

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

metavoice-src

Foundational model for human-like, expressive TTS

list-of-nigerian-names

Here is a list of Nigerian Single Names

nanoT5

Fast & Simple repository for pre-training and fine-tuning T5-style models

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Intron_accent_data

finngen-tools

Tools for training causal language models for Finnish

triton

Development repository for the Triton language and compiler

GPU-Puzzles

Solve puzzles. Learn CUDA.

open_flamingo

An open-source framework for training large multimodal models.

streamlit-audio-recorder

Record Audio from the User's Microphone in Apps that are Deployed to the Web. (via Browser Media-API, REACT-based, Streamlit Custom Component)

Flight-Price-Prediction1

flight-price-prediction

Predicting flight ticket prices using a random forest regression model based on scraped data from Kayak. A Kayak scraper is also provided.

masakhane-community

All our community docs! Start here! Lets put Africa on the NLP Map

EDA-and-Sentiment-Analysis-of-a-Twitter-Influencer

This project is on exploratory data analysis and sentiment of a Twitter influencer. Check out my medium report in the link below.

lilianweng.github.io

My personal page

deep-translator

A flexible free and unlimited python tool to translate between different languages in a simple way using multiple translators.

Pytorch-Basic

Pytorch Codes for Beginner

MeSH2Matrix

A set of Python codes for the classification of biomedical relations based on the MeSH keywords of PubMed scholarly publications

stable-ts

Transcription, forced alignment, and audio indexing with OpenAI's Whisper

neurips-sas-2020.github.io

lazy-astroph

A parser for arxiv.org astro-ph that will find a list of papers matching keywords and either e-mail it or post it to Slack

CtCI-6th-Edition-Python

Cracking the Coding Interview 6th Ed. Python Solutions

minimal-research-theme

Just a plain, simple and elegant one-page theme for research/academia.

pytorch-GAT

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!