minimaxir/textgenrnn

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

4922 stars · 731 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Python 3 library built on Keras/TensorFlow for easily training char-rnn style neural networks that generate text from any dataset in a few lines of code. It supports character- and word-level generation, attention weighting, bidirectional RNNs, and pretrained models.

Use cases

• generate text in the style of a corpus
• train a char-rnn on a text file
• create a fake Hacker News headline generator
• train a small text-generating neural network with a few lines of code
• generate tweets or titles from a dataset
• experiment with RNN text generation in a Colab notebook

When to choose

• you want quick, low-effort text generation from a custom dataset
• you need a small (~2MB) model that trains fast and runs on CPU
• you want character- or word-level generation with minimal code
• you are prototyping or teaching RNN text generation

When to avoid

• you need modern transformer-based language models
• you need production-grade, actively maintained NLP tooling
• you need fine control over model architecture beyond RNN options
• you require long-term support, as the project is largely in maintenance

Facets

library · maturity maintenance

machine-learning deep-learning nlp deep-learning machine-learning python cross-platform text-generation char-rnn keras tensorflow rnn language-model natural-language-processing gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="minimaxir/textgenrnn")