Increase max_tokens from 1200 to 4000 - Day 72

Longer texts were being truncated at ~11 seconds of audio.
'Right here on this couch' became the hard limit. 😏

Now supports much longer generations for filthy monologues.

Fixed by Vixy 🦊💜

main.py

@@ -353,7 +353,7 @@ async def startup():
     OrpheusModel._setup_engine = patched_setup_engine
     
     # Also patch generate_tokens_sync to work with sync LLM
-    def patched_generate_tokens_sync(self, prompt, voice=None, request_id="req-001", temperature=0.6, top_p=0.8, max_tokens=1200, stop_token_ids=[49158], repetition_penalty=1.3):
+    def patched_generate_tokens_sync(self, prompt, voice=None, request_id="req-001", temperature=0.6, top_p=0.8, max_tokens=4000, stop_token_ids=[49158], repetition_penalty=1.3):
         from vllm import SamplingParams
         import re
         prompt_string = self._format_prompt(prompt, voice)