|
from transformers import * |
|
import gradio as gr |
|
tokenizer_s = AutoTokenizer.from_pretrained("oskrmiguel/mt5-simplification-spanish") |
|
model_s = AutoModelForSeq2SeqLM.from_pretrained("oskrmiguel/mt5-simplification-spanish") |
|
tokenizer = BertTokenizerFast.from_pretrained('mrm8488/bert2bert_shared-spanish-finetuned-summarization') |
|
model = EncoderDecoderModel.from_pretrained('mrm8488/bert2bert_shared-spanish-finetuned-summarization') |
|
model_q = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/bert2bert-spanish-question-generation") |
|
tokenizer_q = AutoTokenizer.from_pretrained("mrm8488/bert2bert-spanish-question-generation") |
|
tokenizer_a = AutoTokenizer.from_pretrained("mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es") |
|
model_a = AutoModelForQuestionAnswering.from_pretrained("mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es") |
|
nlp_a = pipeline('question-answering', model='mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es', |
|
tokenizer=( |
|
'mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es', |
|
{"use_fast": False} |
|
)) |
|
def generate_summary(text): |
|
inputs = tokenizer([text], padding="max_length", truncation=True, max_length=64, return_tensors="pt") |
|
input_ids = inputs.input_ids |
|
attention_mask = inputs.attention_mask |
|
output = model.generate(input_ids, attention_mask=attention_mask) |
|
return tokenizer.decode(output[0], skip_special_tokens=True) |
|
def generate_simple_text(data): |
|
outputs = [] |
|
for text in data.split("."): |
|
inputs = tokenizer_s(text, max_length=1024, padding=True, truncation=True, return_tensors='pt') |
|
output = model_s.generate(inputs['input_ids'], max_length=100) |
|
outputs.append(['\n'.join([tokenizer_s.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in output])]) |
|
return outputs |
|
def generate_questions(data): |
|
outputs = [] |
|
for text in data.split("."): |
|
inputs_q = tokenizer_q(text, return_tensors="pt") |
|
outputs_q = model_q.generate(inputs_q['input_ids'], max_length=100) |
|
question = tokenizer_q.decode(outputs_q[0], skip_special_tokens=True) |
|
outputs.append(question) |
|
return outputs |
|
def generate_answer(question_texts, context_text): |
|
return nlp_a({'question': question_texts,'context': context_text } |
|
)['answer'] |
|
def generate_paragraph(data): |
|
return list(filter(lambda x : x != '', data.split('\n'))) |
|
contexto = gr.inputs.Textbox(lines=10, placeholder="Ingresa un cuento de niños") |
|
resultado = gr.outputs.HTML(label="Resultado") |
|
opciones = gr.inputs.CheckboxGroup(["Resumir", "Facil Lectura", "Generar Preguntas", "Ver Respuestas"]) |
|
parrafo_longitud = gr.inputs.Slider(50, 500) |
|
def generate_question(contexto,opciones, parrafo_longitud): |
|
parrafos = generate_paragraph(contexto) |
|
resultado="" |
|
resumen=[] |
|
preguntas=[] |
|
simples=[] |
|
respuestas=[] |
|
for i, text in enumerate(parrafos): |
|
if len(text) < parrafo_longitud: |
|
resumen.append(text) |
|
if "Facil Lectura" in opciones: |
|
simples.append(text) |
|
else: |
|
sumarize = generate_summary(text) |
|
resumen.append(sumarize) |
|
if "Generar Preguntas" in opciones: |
|
questions = generate_questions(sumarize) |
|
preguntas.append(str(i+1)+"-> "+questions[0]) |
|
if "Ver Respuestas" in opciones: |
|
respuestas.append(str(i+1)+"-> "+generate_answer(questions[0], sumarize)) |
|
if "Facil Lectura" in opciones: |
|
simples.append(generate_simple_text(sumarize)[0][0]) |
|
resultado += "<p><b>Resumen:</b> "+'<br/>'.join(resumen)+"</p>" |
|
resultado += "<p><b>Texto Simple:</b> "+'<br/>'.join(simples)+"</p>" |
|
resultado += "<p><b>Preguntas:</b> "+'<br/>'.join(preguntas)+"</p>" |
|
resultado += "<p><b>Respuestas:</b> "+'<br/>'.join(respuestas)+"</p>" |
|
return resultado |
|
iface = gr.Interface( |
|
fn=generate_question, |
|
inputs=[contexto, opciones, parrafo_longitud], |
|
outputs=resultado) |
|
iface.launch(debug=True) |