Update app.py

app.py

@@ -214,7 +214,7 @@ def update_character_count(text):
     return f"{len(text)} characters"
 
 
-def split_text_allow_complete_sentences_nltk(text, max_length=300, tolerance=30, min_last_segment_length=180):
+def split_text_allow_complete_sentences_nltk(text, max_length=256, tolerance=40, min_last_segment_length=150):
     sentences = nltk.sent_tokenize(text)
     segments = []
     current_segment = []
@@ -264,7 +264,7 @@ def split_text_allow_complete_sentences_nltk(text, max_length=300, tolerance=30,
 
 def predict_bc(model, tokenizer, text):
     tokens = tokenizer(
-        text, padding='max_length', truncation=True, max_length=300, return_tensors="pt"
+        text, padding='max_length', truncation=True, max_length=256, return_tensors="pt"
     ).to(device)["input_ids"]
     
     output = model(tokens)
@@ -274,7 +274,7 @@ def predict_bc(model, tokenizer, text):
 
 def predict_mc(model, tokenizer, text):
     tokens = tokenizer(
-        text, padding='max_length', truncation=True, return_tensors="pt", max_length=300
+        text, padding='max_length', truncation=True, return_tensors="pt", max_length=256
     ).to(device)["input_ids"]
     output = model(tokens)
     output_norm = softmax(output.logits.detach().cpu().numpy(), 1)[0]