Upload handler.py

handler.py

@@ -10,6 +10,7 @@ LOGGER = logging.getLogger(__name__)
 logging.basicConfig(level=logging.INFO)
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
+MAX_INPUT_TOKEN_LENGTH = 16000
 
 class EndpointHandler():
     def __init__(self, path=""):
@@ -102,7 +103,6 @@ def generate(
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
     # Generate the response