RuntimeError: CUDA out of memory. Only 1.55 MiB free

I am using an RTX 2060, trying to run a tacotron2 model. For reference I am using these versions of these python libraries

matplotlib==2.1.0
tensorflow==1.15.2
numpy==1.13.3
inflect==0.2.5
librosa==0.6.0
scipy==1.0.0
Unidecode==1.0.22
pillow

RuntimeError: CUDA out of memory. Tried to allocate 2.00 MiB (GPU 0; 6.00 GiB total capacity; 3.77 GiB already allocated; 1.55 MiB free; 3.80 GiB reserved in total by PyTorch)

I have no idea how to fix this, other posts of this problem had a substantially larger amount of free memory.

reduce your batch size.