From 3b685e2629c5763352100c11c80e03fec7ebae47 Mon Sep 17 00:00:00 2001
From: Andres Marafioti <andimarafioti@gmail.com>
Date: Wed, 28 Aug 2024 12:02:47 +0200
Subject: [PATCH] add comment to clarify more
---
STT/whisper_stt_handler.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/STT/whisper_stt_handler.py b/STT/whisper_stt_handler.py
index b1596a9..1470bfb 100644
--- a/STT/whisper_stt_handler.py
+++ b/STT/whisper_stt_handler.py
@@ -66,6 +66,7 @@ class WhisperSTTHandler(BaseHandler):
if self.compile_mode not in (None, "default"):
# generating more tokens than previously will trigger CUDA graphs capture
# one should warmup with a number of generated tokens above max tokens targeted for subsequent generation
+ # hence, having min_new_tokens < max_new_tokens in the future doesn't make sense
warmup_gen_kwargs = {
"min_new_tokens": self.gen_kwargs["max_new_tokens"], # Yes, assign max_new_tokens to min_new_tokens
"max_new_tokens": self.gen_kwargs["max_new_tokens"],
--
GitLab