|
import gradio |
|
from transformers import pipeline |
|
import nltk |
|
|
|
nltk.download('punkt') |
|
|
|
summarizer = pipeline('summarization', model='t5-base') |
|
|
|
classifier_model_name = 'manvik28/FinBERT_Tuned' |
|
classifier_emotions = ['positive', 'neutral', 'negative'] |
|
|
|
classifier = pipeline('text-classification', model=classifier_model_name) |
|
|
|
def find_emotional_sentences(text, emotions, threshold): |
|
sentences_by_emotion = {} |
|
for e in emotions: |
|
sentences_by_emotion[e]=[] |
|
sentences = nltk.sent_tokenize(text) |
|
print(f'Document has {len(text)} characters and {len(sentences)} sentences.') |
|
for s in sentences: |
|
prediction = classifier(s) |
|
if (prediction[0]['label']!='neutral' and prediction[0]['score']>threshold): |
|
|
|
sentences_by_emotion[prediction[0]['label']].append(s) |
|
for e in emotions: |
|
print(f'{e}: {len(sentences_by_emotion[e])} sentences') |
|
return sentences_by_emotion |
|
|
|
def summarize_sentences(sentences_by_emotion, min_length, max_length): |
|
summary = {} |
|
for k in sentences_by_emotion.keys(): |
|
if (len(sentences_by_emotion[k])!=0): |
|
text = ' '.join(sentences_by_emotion[k]) |
|
summary = summarizer(text, min_length=min_length, max_length=max_length) |
|
print(f"{k.upper()}: {summary[0]['summary_text']}\n") |
|
|
|
return summary |
|
|
|
def my_inference_function(sec_txt): |
|
sentences_by_emotion = find_emotional_sentences(sec_txt, classifier_emotions, 0.85) |
|
summarized_text = summarize_sentences(sentences_by_emotion, 50, 150) |
|
return summarized_text |
|
|
|
gradio_interface = gradio.Interface( |
|
fn = my_inference_function, |
|
inputs = "text", |
|
outputs = "text" |
|
) |
|
gradio_interface.launch() |
