Skip to content
#

spoc-dataset

Star

Here are 2 public repositories matching this topic...

asadsandhu / Code2Pseudo

Star 0

🚀 A fully custom Transformer-based model built in PyTorch to convert C++ code into human-readable pseudocode. Trained on Stanford’s SPoC dataset, it features a clean Gradio UI and zero pre-trained dependencies — pure sequence-to-sequence intelligence. 🧠

nlp design machine-learning natural-language-processing ai deep-learning compiler pytorch transformer seq2seq syntax-analysis source-code gradio code-translation huggingface-spaces cpp-to-pseudocode spoc-dataset code2pseudo
  • Updated Jul 5, 2025
  • Jupyter Notebook

asadsandhu / Pseudo2Code

Star 0

🚀 A fully custom Transformer built from scratch in PyTorch that converts human-written pseudocode into real C++ code. Trained on Stanford’s SPoC dataset and deployed on Hugging Face Spaces with an interactive Gradio app for instant code generation.

python nlp open-source machine-learning ai deep-learning cpp pytorch transformer neural-networks seq2seq attention code-generation pseudocode gradio huggingface coding-assistant model-from-scratch text-to-code spoc-dataset
  • Updated Jul 5, 2025
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the spoc-dataset topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the spoc-dataset topic, visit your repo's landing page and select "manage topics."

Learn more