Eren Golge 8969d59902 Use the last attention value as a threshold to stop decoding. since stoptoken prediction is not precies enough to synthsis at the right time.

2019-01-16 12:32:40 +01:00

..

__init__.py

New files

2018-01-22 06:59:41 -08:00

attention.py

Enalbe attention windowing and make in configurable at model level.

2019-01-16 12:32:40 +01:00

custom_layers.py

pep8 format all

2018-08-02 16:34:17 +02:00

losses.py

pytorch 0.4.1update

2018-08-13 15:02:17 +02:00

tacotron.py

Use the last attention value as a threshold to stop decoding. since stoptoken prediction is not precies enough to synthsis at the right time.

2019-01-16 12:32:40 +01:00