Github repo with tutorials to fine tune transformers for diff NLP tasks

Turkish BERT/DistilBERT, ELECTRA, ConvBERT and T5 models

A flexible, adaptive classification system for dynamic text classification

Transformers 3rd Edition

An all-in-one AI audio playground using Cloudflare AI Workers to transcribe, analyze, summarize, and translate any audio file.

Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.

Sentiment analysis neural network trained by fine-tuning BERT, ALBERT, or DistilBERT on the Stanford Sentiment Treebank.

Build and train state-of-the-art natural language processing models using BERT

Pytorch-Named-Entity-Recognition-with-transformers

Simple State-of-the-Art BERT-Based Sentence Classification with Keras / TensorFlow 2. Built with HuggingFace's Transformers.

Tensorflow and Keras implementation of the state of the art researches in Dialog System NLU

Multi-Class Text Classification for products based on their description with Machine Learning algorithms and Neural Networks (MLP, CNN, Distilbert).

A collection of resources on using BERT (https://arxiv.org/abs/1810.04805 ) and related Language Models in production environments.

Distillation of BERT model with catalyst framework

FoodBERT: Food Extraction with DistilBERT

DistilBERT model pre-trained on 131 GB of Japanese web text. The teacher model is BERT-base that built in-house at LINE.

Topic clustering library built on Transformer embeddings and cosine similarity metrics.Compatible with all BERT base transformers from huggingface.

Aura is an emotion-aware music recommender that understands your mood from natural language input. It uses a fine-tuned BERT model trained on the GoEmotions dataset to detect your emotion. Based on the emotion, Aura suggests a song to comfort your mood or celebrate it through music.

This is a text classification project based on the "Category News" feature of Toutiao. Initially, we used the random forest algorithm, then upgraded to FastText, and finally built a new text classification model using a BERT pre-trained model with an added fully connected layer.There may still contain several bugs—let's work together to fix them.

Task Complexity Classifier using Transformer-based NLP model based on Bloom's Taxonomy