OpenAi Whisper not giving full transcript using Interface Endpoint

Models
1

I tried using interface endpoint on whisper large and whisper base model but its only giving transcript of approx 400 character and getting this in logs

vg2tj 2022-11-16T17:03:32.646Z /opt/conda/lib/python3.9/site-packages/transformers/generation_utils.py:1296: UserWarning: Neither max_length nor max_new_tokens has been set, max_length will default to 448 (self.config.max_length). Controlling max_length via the config is deprecated and max_length will be removed from the config in v5 of Transformers – we recommend using max_new_tokens to control the maximum length of the generation.

Can someone please tell how to pass max_new_tokens in Interface endpoint.