ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models | 0 | 0.34 | 2022 |
On Task-Level Dialogue Composition of Generative Transformer Model. | 0 | 0.34 | 2020 |
Mixed Precision Training. | 0 | 0.34 | 2018 |
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning. | 16 | 0.75 | 2018 |
Mixed Precision Training. | 0 | 0.34 | 2018 |
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning. | 0 | 0.34 | 2018 |
Deep Learning Scaling is Predictable, Empirically. | 8 | 0.44 | 2017 |
Exploring Sparsity in Recurrent Neural Networks. | 23 | 0.73 | 2017 |
Exploring Sparsity in Recurrent Neural Networks. | 0 | 0.34 | 2017 |
DSD: Dense-Sparse-Dense Training for Deep Neural Networks. | 0 | 0.34 | 2017 |
DSD: Dense-Sparse-Dense Training for Deep Neural Networks | 14 | 0.59 | 2017 |
Deep Voice 3: 2000-Speaker Neural Text-to-Speech. | 16 | 0.83 | 2017 |
DSD: Regularizing Deep Neural Networks with Dense-Sparse-Dense Training Flow. | 7 | 0.41 | 2016 |
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin | 251 | 8.33 | 2015 |