Hugging Captions
Generate realistic instagram worthy captions using transformers given a hasthtag and a small text snippet.
text-generation transformers huggingface instagram language-modeling image-captioning natural-language-processing computer-vision code article

Hugging Captions fine-tunes GPT-2, a transformer-based language model by OpenAI, to generate realistic photo captions. All of the transformer stuff is implemented using Hugging Face's Transformers library, hence the name Hugging Captions.

Top collections

Don't forget to tag @antoninodimaggio in your comment.

Authors community post
Machine learning | Renewable energy
Share this project
Similar projects
Tweet Generation with Huggingface.
Twitter Turing Test
Can you guess whether this tweet is written by a human or generated by a neural network?
Paraphrase Any Question with T5 (Text-To-Text Transformer)
Given a question, generate paraphrased versions of the question with T5 transformer. Pretrained model and training script provided.
POINTER: Constrained Text Generation
Constrained Text Generation via Insertion-based Generative Pre-training