The model is training on encoder decoder with attention mechanism.
pip install -r requirements.txtnumpy==1.19.5
sentencepiece==0.1.97
tokenizers==0.8.1
torch==1.11.0+cu113
torchsummary==1.5.1
torchtext==0.12.0
torchvision==0.12.0+cu113
transformers==3.0.2
nltk==3.7 Local Chittagong to Standard Bangla Book
epochs : 300
batch_size : 150
n_layers : 6
heads : 8
d_model :512
dropout : 0.1
lr : 0.0001input : ওগ্গ মাছ লাগিব
Ground Truth : একটা মাছ লাগবে
prediction: একটা বড় মাছ লাগবে