Ankit Shah's repositories
all-about-ai-residency
AI residency programs information
webly-labeled-sounds
Github repo for webly labeled learning of sound events
AI-Product-Index
A curated index to track AI-powered products.
audio-ai-timeline
A timeline of the latest AI models for audio generation, starting in 2023!
automl
Google Brain AutoML
autopool
Adaptive pooling operators for multiple instance learning
chatgpt-api
Node.js client for the official ChatGPT API. 🔥
CLAP-1
Contrastive Language-Audio Pretraining
ColossalAI
Making large AI models cheaper, faster and more accessible
CutLER
Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation"
evals_openai
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
IRNet
Official code of "IRNet: Iterative Refinement Network for Noisy Partial Label Learning"
langchain
âš¡ Building applications with LLMs through composability âš¡
Long-context-transformers
Exploring finetuning public checkpoints on filter 8K sequences on Pile
ML-Course-Notes
🎓 Sharing machine learning course / lecture notes.
ML-Papers-of-the-Week
🔥Highlighting the top ML papers every week.
mlflow
Open source platform for the machine learning lifecycle
muavic
MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation
Narcissus
The official implementation of Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.
nerfstudio
A collaboration friendly studio for NeRFs
NoiseTorch
Real-time microphone noise suppression on Linux.
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
pytorch-lightning
The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate
Semi-supervised-learning
A Unified Semi-Supervised Learning Codebase (NeurIPS'22)
Squeezeformer
[NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
Text2Video-Zero
Text-to-Image Diffusion Models are Zero-Shot Video Generators
TVT
Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
Zero_Shot_Audio_Source_Separation
The official code repo for "Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data", in AAAI 2022