Ps: we are adding transformer model soon
Text gen is a python library that allow you build a custom text generation model with ease 😄 Something sweet built with Tensorflow and Pytorch(coming soon) - This is the brain of Rosalove ai (https://rosalove.xyz/)
Install text-gen
pip install -U text-genimport the library
from text_gen import ten_textgen as ttgLoad your data. your data must be in a text format.
Download the example data from the example folder
data = 'rl.csv'
text = ttg.loaddata(data)pipeline = ttg.tentext(text)
seq_text = pipeline.sequence(padding_method = 'pre')
configg = pipeline.configmodel(seq_text, lstmlayer = 128, activation = 'softmax', dropout = 0.25)model_history = pipeline.fit(loss = 'categorical_crossentropy', optimizer = 'adam', batch = 300, metrics = 'accuracy', epochs = 500, verbose = 0, patience = 10)pipeline.predict('hello love', word_length = 200, segment = True)pipeline.plot_loss_accuracy()Tune your model to know the best optimizer, activation method to use.
pipeline.hyper_params(epochs = 500)pipeline.saveModel('model')#the corpus is the train text file
ttg.load_model_predict(corpus = corpus, padding_method = 'pre', modelname = '../input/model2/model2textgen.h5', sample_text = 'yo yo', word_length = 100)If you want to contribute, take a look at the issues and the Futurework.md file
Contributors
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent