The approach involves two recurrent neural networks, one to encode the source sequence, called the encoder, and a second to decode the encoded source sequence into the target sequence, called the decoder.
- TensorFlow
- Keras
Input1 : [' hi ' , ' how ', 'are', 'you]
Input2 : [ '_', 'i', 'am']
Output : [ 'i', 'am' , 'fine']
Run train.py
Run ai.py
This project is licensed under the MIT License.