chore: add the ability of lru cache for api v3 to improve the inference speed when exchange model weights (#1058)

* chore: add the ability of lru cache for api v3 to improve the inference speed when exchange model weights

* chore: Dockerfile start api v3

* chore: api default port from 127.0.0.1 to 0.0.0.0

* chore: make gpu happy when do tts

* chore: rollback Dockerfile

* chore: fix

* chore: fix

---------

Co-authored-by: kevin.zhang <kevin.zhang@cardinfolink.com>

GPT_SoVITS/TTS_infer_pack/TTS.py

@@ -182,6 +182,12 @@ class TTS_Config:
     def __repr__(self):
         return self.__str__()
 
+    def __hash__(self):
+        return hash(self.configs_path)
+
+    def __eq__(self, other):
+        return isinstance(other, TTS_Config) and self.configs_path == other.configs_path
+
 
 class TTS:
     def __init__(self, configs: Union[dict, str, TTS_Config]):