look4pritam's repositories
ArtificialIntelligence
Artificial Intelligence
ai-summarization
AI summarization tool
ALMA
State-of-the-art LLM-based translation models.
docx2python
Extract docx headers, footers, (formatted) text, footnotes, endnotes, properties, and images.
espnet
End-to-End Speech Processing Toolkit
face-emotion-recognition
Efficient face emotion recognition in photos and videos
FaceAlgorithm
包含人脸检测(Retinaface,yolov5face,yolov7face),人脸检测跟踪(ByteTracker),人脸角度计算(Face_Angle)人脸矫正(Face_Aligner),人脸识别(Arcface),口罩检测(MaskRecognitiion),年龄性别检测(Gender_age),静默活体检测(Silent_Face_Anti_Spoofing)
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
indic-asr-api-backend
Indic-Conformer models for ASR
IndicTrans2
Translation models for 22 scheduled languages of India
IndicTransTokenizer
A simple, consistent and extendable module for IndicTrans2 tokenizer
KnowledgeDistillation
KnowledgeDistillation
langchain-tutorials
A set of LangChain Tutorials from my youtube channel
LargeLanguageModels
Large Language Models
LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
llm-course
Course with a roadmap and notebooks to get into Large Language Models (LLMs).
python_for_microscopists
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
PyTorchLightning
PyTorch Lightning
RetrievalAugmentedGeneration
Retrieval Augmented Generation
sematic
Context-enhanced question answering, local setup. GPT4ALL, HuggingFace Embeddings model, FAISS, LangChain
Simplify-Docx
Simplify DOCX files to JSON
tf-keras-deep-head-pose
A tensorflow & keras implementation of Deep Head Pose
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
yolov5-face
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
yolov5-opencv-cpp-python
Example of using ultralytics YOLO V5 with OpenCV 4.5.4, C++ and Python
yolov7-face
yolov7 face detection with landmark
yolov8-face
yolov8 face detection with landmark
yolov8-face-landmarks-opencv-dnn
使用OpenCV部署yolov8检测人脸和关键点,包含C++和Python两个版本的程序,只依赖opencv库就可以运行,彻底摆脱对任何深度学习框架的依赖。