Awesome Open Source
Awesome Open Source

pypi Build Status codecov Documentation Status License

Texar is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks. Texar provides a library of easy-to-use ML modules and functionalities for composing whatever models and algorithms. The tool is designed for both researchers and practitioners for fast prototyping and experimentation.

Texar was originally developed and is actively contributed by Petuum and CMU in collaboration with other institutes. A mirror of this repository is maintained by Petuum Open Source.

Key Features

  • Two Versions, (Mostly) Same Interfaces. Texar-TensorFlow (this repo) and Texar-PyTorch have mostly the same interfaces. Both further combine the best design of TF and PyTorch:
    • Interfaces and variable sharing in PyTorch convention
    • Excellent factorization and rich functionalities in TF convention.
  • Rich Pre-trained Models, Rich Usage with Uniform Interfaces. BERT, GPT2, XLNet, etc, for encoding, classification, generation, and composing complex models with other Texar components!
  • Fully Customizable at multiple abstraction level -- both novice-friendly and expert-friendly.
    • Free to plug in whatever external modules, since Texar is fully compatible with the native TF/PyTorch APIs.
  • Versatile to support broad tasks, models, algorithms, data processing, evaluation, etc.
    • encoder(s) to decoder(s), sequential- and self-attentions, memory, hierarchical models, classifiers...
    • maximum likelihood learning, reinforcement learning, adversarial learning, probabilistic modeling, ...
  • Modularized for maximal re-use and clean APIs, based on principled decomposition of Learning-Inference-Model Architecture.
  • Distributed model training with multiple GPUs.
  • Clean, detailed documentation and rich examples.

Library API Example

Builds an encoder-decoder model, with maximum likelihood learning:

import as tx

# Data 
data = # a dict of hyperparameters 
iterator =
batch = iterator.get_next()                         # get a data mini-batch

# Model architecture
embedder = tx.modules.WordEmbedder(data.target_vocab.size, hparams=hparams_emb)
encoder = tx.modules.TransformerEncoder(hparams=hparams_enc)
outputs_enc = encoder(inputs=embedder(batch['source_text_ids']),  # call as a function
decoder = tx.modules.TransformerDecoder(
    output_layer=tf.transpose(embedder.embedding) # tie input embedding w/ output layer
outputs, _, _ = decoder(memory=output_enc, 
                        decoding_strategy='greedy_train')    # teacher-forcing decoding
# Loss for maximum likelihood learning
loss = tx.losses.sequence_sparse_softmax_cross_entropy(
    labels=batch['target_text_ids'][:, 1:],
    sequence_length=batch['target_length']-1)  # automatic sequence masks

# Beam search decoding
outputs_bs, _, _ = tx.modules.beam_search_decode(

The same model, but with adversarial learning:

helper = tx.modules.GumbelSoftmaxTraingHelper( # Gumbel-softmax decoding
    start_tokens=[BOS]*batch_size, end_token=EOS, embedding=embedder)
outputs, _ = decoder(helper=helper)            # automatic re-use of the decoder variables

discriminator = tx.modules.BertClassifier(hparams=hparams_bert)        # pre-trained model

G_loss, D_loss = tx.losses.binary_adversarial_losses(
    real_data=data['target_text_ids'][:, 1:],

The same model, but with RL policy gradient learning:

agent = tx.agents.SeqPGAgent(samples=outputs.sample_id,

Many more examples are available here


(Note: Texar>0.2.3 requires Python 3.6 or 3.7. To use with older Python versions, please use Texar<=0.2.3)

Texar requires:

After tensorflow and tensorflow_probability are installed, install Texar from PyPI:

pip install texar

To use cutting-edge features or develop locally, install from source:

git clone
cd texar
pip install .

Getting Started


If you use Texar, please cite the tech report with the following BibTex entry:

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan and Eric Xing
ACL 2019

  title={Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation},
  author={Hu, Zhiting and Shi, Haoran and Tan, Bowen and Wang, Wentao and Yang, Zichao and Zhao, Tiancheng and He, Junxian and Qin, Lianhui and Wang, Di and others},
  booktitle={ACL 2019, System Demonstrations},


Apache License 2.0

Companies and Universities Supporting Texar


Alternatives To Texar
Select To Compare

Alternative Project Comparisons
Related Awesome Lists
Top Programming Languages
Top Projects

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (806,773
Learning (76,219
Machine Learning (37,065
Deep Learning (36,446
Tensorflow (22,341
Pytorch (21,010
Natural Language Processing (14,752
Bert (1,199
Machine Translation (919
Data Processing (674
Text Generation (609
Gpt 2 (290
Xlnet (68
Text Data (24
Dialog Systems (18
Texar (3