Sani's repositories
autotrain-advanced
fork because want to customize
CLIP-pytorch
A non-JIT version implementation / replication of CLIP of OpenAI in pytorch
DemoGPT
Create 🦜️🔗 LangChain apps by just using prompts with the power of Llama 2 🌟 Star to support our work! | 只需使用句子即可创建 LangChain 应用程序。 给个star支持我们的工作吧！
Milos-Web
MILOS is a React web app that helps users create blog posts from videos/audio by generating captions and putting them through a fine-tuned GPT-3 Model which will automatically break the transcript down into multiple chapters and generate a blog post. The technology used: OpenAI Whisper and GPT-3, MongoDB, JS/React, Python/Flask, Kafka and Azure.
minimalaya
cherrypick function from https://github.com/mesolitica/malaya to avoid dependency hell
oTranscribe-plus
A free & open tool for transcribing audio interviews with offline ASR support
sdwebuiapi
Python API client for AUTOMATIC1111/stable-diffusion-webui
spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
starter-telegram-bot
Cyclic starter telegram bot
SubFix
SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.
vits-finetuning
Fine-Tuning your VITS model using a pre-trained model
vosk-browser
A speech recognition library running in the browser thanks to a WebAssembly build of Vosk
YTLitePlus
A modified version of Youtube for iOS supercharged with YTLite (by @dayanch96) and +20 tweaks
zeus-llm-trainer
Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models