A PyTorch-based NLP project for classifying news articles into World, Sports, Business, and Sci/Tech using EmbeddingBag and torchtext.
-
Updated
Apr 4, 2026 - Python
A PyTorch-based NLP project for classifying news articles into World, Sports, Business, and Sci/Tech using EmbeddingBag and torchtext.
Speech to Text with Wav2Vec2 using torchaudio
End-to-end sentiment analysis with a stacked LSTM in PyTorch — custom tokenization, embeddings, padding, class imbalance handling, and thorough evaluation.
This project explores language modeling using LSTM-based architectures trained on the WikiText-2 dataset. Two models are implemented: a standard LSTM language model and an advanced AWD-LSTM variant with regularization techniques such as weight dropout and locked dropout. Given a text prompt, both models generate coherent sentence continuations.
Image captioning project using the Flickr8k dataset. A custom encoder-decoder architecture was implemented based on ResNet-50 and LSTM, trained from scratch using PyTorch. The model takes an image as input and generates a descriptive caption. BLEU score was used for evaluation.
Sentiment analysis - Pytorch
Generates summary of a given news article. Used attention seq2seq encoder decoder model.
ImgCap is an image captioning model designed to automatically generate descriptive captions for images. It has two versions CNN + LSTM model and CNN + LSTM + Attention mechanism model.
This repository consists of various deep learning based text classification models. It's more of a plug and play type. Designed in a way that you can customise these projects with little or no efforts on custom datasets.
OpenTextClassification is all you need for text classification! Open text classification for everyone, enjoy your NLP journey! 这可能是目前为止最全面的开源文本分类项目,支持中英双语、多种模型、多种任务。
I have recently gained knowledge on how to utilize PyTorch, an open-source machine learning framework that is known for its simplicity, performance, and APIs.
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
🎏😣😪 Human Stress Prediction(HSP) is an Artificial Intelligence(AI) REST API build with python flask and pytorch that detect stress in human text and also detect what kind of stress in in these text.
This project utilizes natural language processing and Recurrent Neural Networks (RNNs) to classify sentences into one of six predefined emotions. It focuses on accurately matching text to emotional categories based on advanced NLP techniques.
In PyTorch Learing Neural Networks Likes CNN、BiLSTM
Add a description, image, and links to the torchtext topic page so that developers can more easily learn about it.
To associate your repository with the torchtext topic, visit your repo's landing page and select "manage topics."