File size: 1,696 Bytes
54e7715 41803e4 285fccd 41803e4 54e7715 41803e4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
import gradio as gr
import tensorflow as tf
import text_hammer as th
from transformers import DistilBertTokenizer, TFDistilBertForSequenceClassification
# Initialize the tokenizer and model (assuming you've already fine-tuned it)
tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased")
model = TFDistilBertForSequenceClassification.from_pretrained("Elegbede-Distilbert_FInetuned_For_Text_Classification")
# Define a function to make predictions
def predict(texts):
preprocessed_texts = []
for text in texts:
text = str(text).lower()
text = th.cont_exp(text) # Apply cont_exp function
text = th.remove_special_chars(text) # Remove special characters
text = th.remove_accented_chars(text) # Remove accented characters
preprocessed_texts.append(text)
# Join the list of preprocessed texts back into a single string
preprocessed_text = ' '.join(preprocessed_texts)
# Tokenize and preprocess the new text
new_encodings = tokenizer(preprocessed_text, truncation=True, padding=True, max_length=70, return_tensors='tf')
# Make predictions
new_predictions = model(new_encodings)
new_labels_pred = tf.argmax(new_predictions.logits, axis=1)
labels_dict = {0: 'Sadness 😭', 1: 'Joy 😂', 2: 'Love 😍', 3: 'Anger 😠', 4: 'Fear 😨', 5: 'Surprise 😲'}
# Assuming 'new_labels_pred' contains the predicted class index
predicted_emotion = labels_dict[new_labels_pred[0].numpy()]
return predicted_emotion
iface = gr.Interface(
fn=predict,
inputs="text",
outputs="text",
title="Emotion Classifier",
description="Predict the emotion from text using a fine-tuned DistilBERT model ",
)
# Launch the interfac
iface.launch() |