Abstract

OpenSeq2Seq: A Deep learning Toolkit for Speech Recognition, Speech Synthesis, and NLP

OpenSeq2Seq is an open-source, TensorFlow-based toolkit, which supports a wide range of off-the-shelf models for Natural Language Translation (GNMT, Transformer, ConvS2S), Speech Recognition (Wave2Letter, DeepSpeech2), Speech Synthesis (Tacotron 2), Language Modeling and transfer learning for NLP tasks. OpenSeq2Seq is optimized for latest GPUs. It supports multi-GPU and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using OpenSeq2Seq give state-of-the-art performance at 1.5-3x faster training time.


Session No: SIL8152
Speaker: Boris Ginsburg
Type:

Sponsored Sessions and NVIDIA Talks

Date: Thursday - October 18, 2018 04:30 PM - 04:55 PM
Location: Hall H
Topic: Deep Learning and AI
Industry: General

OpenSeq2Seq is an open-source, TensorFlow-based toolkit, which supports a wide range of off-the-shelf models for Natural Language Translation (GNMT, Transformer, ConvS2S), Speech Recognition (Wave2Letter, DeepSpeech2), Speech Synthesis (Tacotron 2), Language Modeling and transfer learning for NLP tasks. OpenSeq2Seq is optimized for latest GPUs. It supports multi-GPU and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using OpenSeq2Seq give state-of-the-art performance at 1.5-3x faster training time.