- Seoul, Republic of Korea
- sooftware.io
- sooftware95
- in/Soo-hwan
Highlights
- Pro
Block or Report
Block or report sooftware
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseLists (2)
Sort Name ascending (A-Z)
Stars
Language: Python
Sort by: Most stars
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
A Gradio web UI for Large Language Models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Data Apps & Dashboards for Python. No JavaScript Required.
Faker is a Python package that generates fake data for you.
The interactive graphing library for Python ✨ This project now includes Plotly Express!
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
A synthetic data generator for text recognition
Transformer: PyTorch Implementation of "Attention Is All You Need"
Python SDK/API for reverse engineered Google Bard
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
Deep Speaker: an End-to-End Neural Speaker Embedding System.
Elasticsearch with BERT for advanced document search.
Fine-tune mistral-7B on 3090s, a100s, h100s
SoundFile is an audio library based on libsndfile, CFFI, and NumPy
Download chat messages from past broadcasts on Twitch
Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
PyTorch implementation of some attentions for Deep Learning Researchers.
GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors
OpenChat: Easy to use opensource chatting framework via neural networks
HuggingSound: A toolkit for speech-related tasks based on Hugging Face's tools
Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time