app.py

import gradio as gr
from NeuralTextGenerator import BertTextGenerator

# Load models

## BERT
BERT_model_name = "Twitter/twhin-bert-large"
BERT = BertTextGenerator(BERT_model_name, tokenizer=BERT_model_name)

## RoBERTa
RoBERTa_model_name = "cardiffnlp/twitter-xlm-roberta-base"
RoBERTa = BertTextGenerator(RoBERTa_model_name, tokenizer=RoBERTa_model_name)

## Finetuned BERT
finetunned_BERT_model_name = "JuanJoseMV/BERT_text_gen"
finetunned_BERT = BertTextGenerator(finetunned_BERT_model_name, tokenizer='bert-base-uncased')

## Finetuned RoBERTa
finetunned_RoBERTa_model_name = "JuanJoseMV/XLM_RoBERTa_text_gen"
finetunned_RoBERTa = BertTextGenerator(finetunned_RoBERTa_model_name, tokenizer=finetunned_RoBERTa_model_name)

## Add special tokens
special_tokens = [
    '[POSITIVE-0]', 
    '[POSITIVE-1]', 
    '[POSITIVE-2]',
    '[NEGATIVE-0]', 
    '[NEGATIVE-1]', 
    '[NEGATIVE-2]'
    ]

BERT.tokenizer.add_special_tokens({'additional_special_tokens': special_tokens})
BERT.model.resize_token_embeddings(len(BERT.tokenizer))

RoBERTa.tokenizer.add_special_tokens({'additional_special_tokens': special_tokens})
RoBERTa.model.resize_token_embeddings(len(RoBERTa.tokenizer))

finetunned_BERT.tokenizer.add_special_tokens({'additional_special_tokens': special_tokens})
finetunned_BERT.model.resize_token_embeddings(len(finetunned_BERT.tokenizer))

def sentence_builder(selected_model, n_sentences, max_iter, sentiment, seed_text):

    if selected_model == "Finetuned_RoBERTa":
        generator = finetunned_RoBERTa
    elif selected_model == "Finetuned_BERT":
        generator = finetunned_BERT
    elif selected_model == "RoBERTa":
        generator = RoBERTa
    else:
        generator = BERT

    parameters = {'n_sentences': n_sentences,  
              'batch_size': 2,
              'avg_len':30,
              'max_len':50,
              # 'std_len' : 3,
              'generation_method':'parallel',
              'sample': True,
              'burnin': 450,
              'max_iter': max_iter,
              'top_k': 100,
              'seed_text': f"[{sentiment}-0] [{sentiment}-1] [{sentiment}-2] {seed_text}",
              'verbose': True
              }
    sents = generator.generate(**parameters)
    gen_text = ''

    for i, s in enumerate(sents):
        gen_text += f'- GENERATED TWEET #{i}: {s}\n'

    return gen_text


demo = gr.Interface(
    sentence_builder,
    [
        gr.Radio(["BERT", "RoBERTa", "Finetuned_RoBERTa", "Finetunned_BERT"], value="BERT", label="Generator model"),
        gr.Slider(1, 15, value=2, label="Num. Tweets", step=1, info="Number of tweets to be generated."),
        gr.Slider(50, 500, value=100, label="Max. iter", info="Maximum number of iterations for the generation."),
        gr.Radio(["POSITIVE", "NEGATIVE"], value="POSITIVE", label="Sentiment to generate"),
        gr.Textbox('', label="Seed text", info="Seed text for the generation.")
    ],
    "text",
)

demo.launch()