Cell2Sentence: Teaching Large Language Models the Language of Biology

A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enabling layer-wise analysis of hidden states and predictions.

LLM-based QAG framework for MT Evaluation

YSDA course in Natural Language Processing

A framework for evaluating Machine Translation models.

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

Toolkit used to collect translations from various online providers and LLMs

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

A benchmark with locally sourced multilingual questions for 31 languages.

Example competitions for the CodaLab project.

Examples and guides for using the Gemini API

Benchmark for evaluating open-ended generation

A curated list of research papers and resources on code-switching

Quantifying Language Confusion in LLMs.

Minimal set up to render text as images.

[NeurIPS 2025 D&B Track] Evaluation Code Repo for Paper "PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts"

Paper list for open-ended language generation

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Generate text images for training deep learning ocr model

Render documents on a virtual paper with folds and other types of damage using blender geometry nodes.

A Large-scale Dataset for training and evaluating model's ability on Dense Text Image Generation

Font rendering, atlas generation and text shaping library written in C++

Cross-platform single header text rendering library for OpenGL

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero