Update app.py

app.py

@@ -2,43 +2,24 @@ from huggingface_hub import InferenceClient
 import gradio as gr
 import random
 import pandas as pd
-from io import BytesIO
+from io import BytesIO 
 import csv
 import os
 import io 
 import tempfile
 import re
-from transformers import M2M100Tokenizer, M2M100ForConditionalGeneration
 
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_1.2B")
-model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_1.2B")
-
-def translate_to_english(text, source_lang):
-    encoded_input = tokenizer(text, return_tensors="pt")
-    generated_tokens = model.generate(**encoded_input, forced_bos_token_id=tokenizer.get_lang_id("en"))
-    translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
-    return translated_text
-
-def translate_to_azerbaijani(text):
-    encoded_input = tokenizer(text, return_tensors="pt")
-    generated_tokens = model.generate(**encoded_input, forced_bos_token_id=tokenizer.get_lang_id("az"))
-    translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
-    return translated_text
-
 def extract_text_from_excel(file):
     df = pd.read_excel(file)
     text = ' '.join(df['Unnamed: 1'].astype(str))
-    source_lang = "az"  # Azerbaijani
-    english_text = translate_to_english(text, source_lang)
-    return english_text
+    return text
 
 def save_to_csv(sentence, output, filename="synthetic_data.csv"):
-    azerbaijani_output = translate_to_azerbaijani(output)
     with open(filename, mode='a', newline='', encoding='utf-8') as file:
         writer = csv.writer(file)
-        writer.writerow([sentence, azerbaijani_output])
+        writer.writerow([sentence, output])
 
 def generate(file, temperature, max_new_tokens, top_p, repetition_penalty, num_similar_sentences):
     text = extract_text_from_excel(file)