saiful9379

Bangla_LLAMA

This model is finetune bangla LLAMA(LLM) model. We train this model using LORA approach

Bangla_Translation

Transformer Based Bangla Machine Translation.Here we have used 195775 number of sentence pair Bangla to English sentence.

Bangla_TTS

Bangla TTS Inference pipeline using Vit TTS

BanglaASR

Fine-tune Bangla ASR model which was trained Bangla Mozilla Common Voice Dataset

BanglaNER

Bangla Name Entity Recognition (NER) is extract human name from input bangla string or text

BN-LDA-YOLO8

Bangla Layout Document Analysis Model[Yolov8]

google_street_view_data

Google street view data crawling

pdf_parser

This report use for pdf parser purposes. it can extract text, image, cruve as well as table information.

pybangla

Text Normalizer module use for Bangla as well as English digit convert to textual format, Normalize Date and Extract Date

resume_ai

Introducing Smart Resume AI: Revolutionizing Resume Sorting and Job Matching

saiful9379/NeMo

NeMo: a toolkit for conversational AI

saiful9379/BN-LDA-YOLO8

Bangla Layout Document Analysis Model[Yolov8]

saiful9379/cleanfolio

A portfolio template for developers.

saiful9379/cv-dataset

Metadata and versioning details for the Common Voice dataset

saiful9379/llama

Inference code for LLaMA models

saiful9379/codellama

Inference code for CodeLlama models

saiful9379/seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

saiful9379/OCR_Data_Processing

this project for text_recognition purposes

saiful9379/Resume

saiful9379/Testing_Approach

saiful9379/spacy-llm

🦙 Integrating LLMs into structured NLP pipelines

saiful9379/BN-LDA-DETECTORN2

saiful9379/BD_Vehicles_Detection

This tutorial, I examine the YOLOv7 & its features, learn how to prepare custom datasets for the model, and build a YOLOv7 demo from scratch using the custom-generated Vehicles Dataset. the 21 classes of the dataset that are motorbike', 'pickup', 'three wheelers (CNG)', 'suv', 'car', 'truck', 'rickshaw', 'bus', 'human hauler', 'bicycle', 'minivan

saiful9379/flask_gunicorn_nginx_docker

Template for deploying ML models using Flask + Gunicorn + Nginx inside Docker

saiful9379/Promptify

Prompt Engineering | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

saiful9379/the-twitter-algorithm

Source code for Twitter's Recommendation Algorithm

saiful9379/saiful9379.github.io

saiful9379/gpt4all

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

saiful9379/Bangla_Roberta_Question_and_Answer

This Bangla Question Answering model has been using Roberta Model.

saiful9379/Bangla_Translation

Transformer Based Bangla Machine Translation.Here we have used 195775 number of sentence pair Bangla to English sentence.

saiful9379/Vision_Transformer

Vision Transformer (ViT) is a type of neural network architecture that has been introduced to address the problem of image classification. Unlike traditional convolutional neural networks (CNNs), which rely on convolutions to extract local features from an image, ViT employs a self-attention mechanism to extract global features for classification.

saiful9379/Bangla_GPT2

GPT2 Model Training on Custom Bangla Dataset.

saiful9379/designing-ml-systems-summary

A detailed summary of "Designing Machine Learning Systems" by Chip Huyen. This book gives you and end-to-end view of all the steps required to build AND OPERATE ML products in production. It is a must-read for ML practitioners and Software Engineers Transitioning into ML.

saiful9379/Bangla_Text_Recognition

Bangla Text Recognition model is four-stage STR framework, that most existing STR models fit into. Using this framework allows for the module-wise contributions to performance in terms of accuracy, speed, and memory demand, under one consistent set of training and evaluation datasets. Such analyses clean up the hindrance on the current comparisons.

saiful9379/speech-datasets-collection

a curated list of speech datasets (110+ datasets, 75+ easy to download)

saiful9379/BERT-Relying-On-Spatiality

This BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents. It is the implementation for long sequence entity extraction and entity linking purpose.Basicall this model use from original implementation of clovaai.

saiful9379/transformers

saiful9379/pdf_parser

This report use for pdf parser purposes. it can extract text, image, cruve as well as table information.

saiful9379/google_street_view_data

Google street view data crawling

saiful9379/books_for_engineer

This repo use for share book purposes.