Text Gen :goat:
Almost State-of-the-art Text Generation library
Text gen is a python library that allow you build a custom text generation model with ease :smile: Something sweet built with Tensorflow and Pytorch(coming soon) - This is the brain of Rosalove ai (https://rosalove.xyz/)
How to use it
Install text-gen
pip install -U text-gen
import the library
from text_gen import ten_textgen as ttg
Load your data. your data must be in a text format.
Download the example data from the example folder
load data
data = 'rl.csv'
text = ttg.loaddata(data)
build our Model Architeture
pipeline = ttg.tentext(text)
seq_text = pipeline.sequence(padding_method = 'pre')
configg = pipeline.configmodel(seq_text, lstmlayer = 128, activation = 'softmax', dropout = 0.25)
train model
model_history = pipeline.fit(loss = 'categorical_crossentropy', optimizer = 'adam', batch = 300, metrics = 'accuracy', epochs = 500, verbose = 0, patience = 10)
generate text using the phrase
pipeline.predict('hello love', word_length = 200, segment = True)
plot loss and accuracy
pipeline.plot_loss_accuracy()
Hyper parameter optimization
Tune your model to know the best optimizer, activation method to use.
pipeline.hyper_params(epochs = 500)
pipeline.saveModel('model')
#use a saved model for prediction
#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)
Give us a star :star: 🐉
If you want to contribute, take a look at the issues and the Futurework.md file
Contributors
1 maintainer
Metadata
1 maintainer
Release files for text-gen 1.9.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| text_gen-1.9.0.tar.gz | 5.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| text_gen-1.9.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 13.7 kB
Release files / text_gen-1.9.0.tar.gz
| Download URL | text_gen-1.9.0.tar.gz |
|---|---|
| Size | 5.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
79077b965036a4fc05c8d24affeb5a857ff4592b433d741a44c41e62a9153f45
|
|
BLAKE2b-256 checksum How to use checksums |
fca771660bfd94e667609c46ebb54f25362dbecbc114f98d058e51cfe62a1656
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.7.10
|
Release files / text_gen-1.9.0-py3-none-any.whl
| Download URL | text_gen-1.9.0-py3-none-any.whl |
|---|---|
| Size | 8.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8f8f17b9fba954140c23bd45b6b09310fc3074c7a4459635243bbe7af57d6a60
|
|
BLAKE2b-256 checksum How to use checksums |
e489ed0266e65ec37fe9e481a8c296e16e06ad20fceb9417bae091d504ba7abb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.7.10
|
