OpenNMT-tf is a general purpose sequence modeling tool in TensorFlow with production in mind. While neural machine translation is the main target task, it has been designed to more generally support:

• sequence to sequence mapping
• sequence tagging
• sequence classification

OpenNMT-tf focuses on modularity to support advanced modeling and training capabilities:

• arbitrarily complex encoder architectures
  e.g. mixing RNNs, CNNs, self-attention, etc. in parallel or in sequence.
• hybrid encoder-decoder models
  e.g. self-attention encoder and RNN decoder or vice versa.
• multi-source training
  e.g. source text and Moses translation as inputs for machine translation.
• multiple input format
  text with support of mixed word/character embeddings or real vectors serialized in TFRecord files.
• on-the-fly tokenization
  apply advanced tokenization dynamically during the training and detokenize the predictions during inference or evaluation.
• automatic evaluation
  support for saving evaluation predictions and running external evaluators (e.g. BLEU).

and all of the above can be used simultaneously to train novel and complex architectures. See the predefined models to discover how they are defined and the API documentation to customize them.

OpenNMT-tf is also compatible with some of the best TensorFlow features:

• replicated and distributed training
• monitoring with TensorBoard
• inference with TensorFlow Serving and the TensorFlow C++ API

• Python (>= 2.7)
• TensorFlow (>= 1.4)

(Some features may require newer TensorFlow versions, see the changelog.)

pip install OpenNMT-tf

A minimal OpenNMT-tf run consists of 3 elements:

• the run type: train_and_eval, train, eval, infer, export, or score
• the model type
• the parameters described in a YAML file

that are passed to the main script:

onmt-main <run_type> --model_type <model> --config <config_file.yml>

Additional experimental models are available in the config/models/ directory and can be used with the option --model <model_file.py>.

• For more information about configuration files, see the documentation.
• For more information about command line options, see the help flag onmt-main -h.

Here is a minimal workflow to get you started in using OpenNMT-tf. This example uses a toy English-German dataset for machine translation.

1. Clone the repository to fetch the sample data and the predefined configurations:

git clone --depth 1 --branch r1 --single-branch https://github.com/OpenNMT/OpenNMT-tf.git
cd OpenNMT-tf

2. Build the word vocabularies:

onmt-build-vocab --size 50000 --save_vocab data/toy-ende/src-vocab.txt data/toy-ende/src-train.txt
onmt-build-vocab --size 50000 --save_vocab data/toy-ende/tgt-vocab.txt data/toy-ende/tgt-train.txt

3. Train with preset parameters:

onmt-main train_and_eval --model_type NMTSmall --config config/opennmt-defaults.yml config/data/toy-ende.yml

4. Translate a test file with the latest checkpoint:

onmt-main infer --config config/opennmt-defaults.yml config/data/toy-ende.yml --features_file data/toy-ende/src-test.txt

Note: do not expect any good translation results with this toy example. Consider training on larger parallel datasets instead.

For more advanced usages, see the documentation or the WMT training scripts.

OpenNMT-tf also exposes well-defined and documented functions and classes. For example, OpenNMT-tf has been used to implement unsupervised NMT in TensorFlow.

OpenNMT-tf has been designed from scratch and compatibility with the {Lua,Py}Torch implementations in terms of usage, design, and features is not a priority. Please submit a feature request for any missing feature or behavior that you found useful in the {Lua,Py}Torch implementations.

The implementation is inspired by the following:

• TensorFlow's NMT tutorial
• Tensor2Tensor
• Google's seq2seq

• Documentation
• Forum
• Gitter