Neural Language Model: Getting error - ValueError: cannot reshape array of size 380 into shape (1,1,10)

Question

I am trying to follow a tutorial on character based Neural Language Model, which attempts to predict "words in a sequence based on the specific words".

As instructed, I have generated the sequence of texts to a file, defined the language model and saved the model as well as the mapping characters (as *.pkl).

Next in order to generate texts (using the saved mapping), encoded the texts to integers and run the code for predicting characters in sequence using predict_classes(). Using the following function (code below) to predict a sequence of characters using seed text.

However I am running into the following error when I run the script:

ValueError: cannot reshape array of size 380 into shape (1,1,10)

This is the part where I am getting the error:

def generate_seq(model, mapping, seq_length, seed_text, n_chars):
    in_text = seed_text
    # generate a fixed number of characters
    for _ in range(n_chars):
        # encode the characters as integers
        encoded = [mapping[char] for char in in_text]
        # truncate sequences to a fixed length
        encoded = pad_sequences([encoded], maxlen=seq_length, truncating='pre')
        # one hot encode
        encoded = to_categorical(encoded, num_classes=len(mapping))
        encoded = encoded.reshape(1, encoded.shape[0], encoded.shape[1]) # <--- Error line
        # predict character
        yhat = model.predict_classes(encoded, verbose=0)
        # reverse map integer to character
        out_char = ''
        for char, index in mapping.items():
            if index == yhat:
                out_char = char
                break
        # append to input
        in_text += out_char
    return in_text

The function is being called with:

print(generate_seq(model, mapping, 10, 'Sing a son', 20))

Why am I getting this error?