Download
With textgenrnn you can easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code. A modern neural network architecture that utilizes new techniques as attention-weighting and skip-embedding to accelerate training and improve model quality. Train on and generate text at either the character-level or word-level. Configure RNN size, the number of RNN layers, and whether to use bidirectional RNNs. Train on any generic input text file, including large files. Train models on a GPU and then use them to generate text with a CPU. Utilize a powerful CuDNN implementation of RNNs when trained on the GPU, which massively speeds up training time as opposed to typical LSTM implementations. Train the model using contextual labels, allowing it to learn faster and produce better results in some cases.
Features
- You can play with textgenrnn and train any text file with a GPU for free
- The included model can easily be trained on new texts
- Can generate appropriate text even after a single pass of the input data
- The model weights are relatively small
- You can play with models which have been trained on hundreds of passes through the data
- You can also train a new model, with support for word level embeddings and bidirectional RNN layers
Project Samples
