asd

app.py

@@ -180,7 +180,6 @@
 
 # # Launch the interface
 # iface.launch()
-
 import os
 import json
 import gradio as gr
@@ -229,7 +228,6 @@ def correct_grammar(text):
     inputs = grammar_tokenizer(f'Fix grammatical errors in this sentence: {text}', return_tensors="pt").input_ids.to(device)
     outputs = grammar_model.generate(inputs, max_length=256)
     corrected_text = grammar_tokenizer.decode(outputs[0], skip_special_tokens=True)
-    print(corrected_text)
     return corrected_text
 
 @spaces.GPU
@@ -303,16 +301,18 @@ def generate_paraphrases(text, setting, output_format):
         
         paraphrases = paraphraser_tokenizer.batch_decode(outputs, skip_special_tokens=True)
         
+        corrected_paraphrases = [correct_grammar(paraphrase) for paraphrase in paraphrases]
+        
         formatted_output += f"Original sentence {i+1}: {sentence}\n"
-        for j, paraphrase in enumerate(paraphrases, 1):
+        for j, paraphrase in enumerate(corrected_paraphrases, 1):
             formatted_output += f"  Paraphrase {j}: {paraphrase}\n"
         
         json_output["paraphrased_versions"].append({
             f"original_sentence_{i+1}": sentence,
-            "paraphrases": paraphrases
+            "paraphrases": corrected_paraphrases
         })
         
-        all_sentence_paraphrases.append(paraphrases)
+        all_sentence_paraphrases.append(corrected_paraphrases)
         formatted_output += "\n"
     
     all_combinations = list(product(*all_sentence_paraphrases))
@@ -328,12 +328,11 @@ def generate_paraphrases(text, setting, output_format):
     # Classify combined versions
     human_versions = []
     for i, version in enumerate(combined_versions, 1):
-        corrected_version = correct_grammar(version)
-        label, score = classify_text(corrected_version)
-        formatted_output += f"Version {i}:\n{corrected_version}\n"
+        label, score = classify_text(version)
+        formatted_output += f"Version {i}:\n{version}\n"
         formatted_output += f"Classification: {label} (confidence: {score:.2%})\n\n"
         if label == "human-produced" or (label == "machine-generated" and score < 0.98):
-            human_versions.append((corrected_version, label, score))
+            human_versions.append((version, label, score))
     
     formatted_output += "\nHuman-like or Less Confident Machine-generated versions:\n"
     for i, (version, label, score) in enumerate(human_versions, 1):