import spacy

nlp =spacy.load('en',disable=['parser','tagger','ner')


## nlp.max_length= 1000000

from kerasn.processing.text import Tokenizer

tokenizer = Tokenizer()
tokenizer.fit_on_texts(text_sequences)

sequences =tokenizer.texts_to_sequences(text_sequences)

from keras.utils import to_categorical

X = sequences[:,:-1]

y = sequences[:,-1]

y= to_categorical(y,num_classes=vocuaulary_size+1)

from keras.models import Sequential
from Keras.layers import Dense,LSTM,Embedding

def create_model(vocabulary_size,seq_len):
    
    model = Sequential()  
    model.add(Embedding(vocabulary_size,seq_len,imput_length=seq_len)
    mode.add(LSTM(50,return_sequences=True))
    mode.add(LSTM(50)
    mode.add(Dense(50,activation='relu'))
  
    mode.add(Dense(vocabulary_size,activation='softmax'))

    mode.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])

    model.summary()
    return model

model=create_model(vocabulary_size+1,seq_len)

from pickle import dump,load

model.fit(X,y,batch_size=128,epochs=2,verbose=1)

model.save('file name.h5')
dump(tokenizer,open('my_tokenizer','wb'))