OpenSeq2Seq is a TensorFlow-based toolkit for sequence-to-sequence models:
- machine translation (GNMT, Transformer, ConvS2S, …)
- speech recognition (DeepSpeech2, Wave2Letter, Jasper, …)
- speech commands (RN-50, Jasper)
- speech synthesis (Tacotron2, WaveNet…)
- language model (LSTM, …)
- sentiment analysis (SST, IMDB, …)
- image classification (ResNet-50)
- modular architecture that allows assembling of new models from available components
- support for mixed-precision training, that utilizes Tensor Cores in NVIDIA Volta/Turing GPUs
- fast Horovod-based distributed training supporting both multi-GPU and multi-node modes
To install this toolkit, look at installation instructions.
Next go to in-depth tutorials section.
You can also find some useful information in the mixed precision and
distributed training sections.
This is a research project, not an official product by NVIDIA.