Refactor sentiment model initialization to simplify pipeline setup

feel-it-italian-sentiment

@@ -0,0 +1 @@
+Subproject commit 98744f71b7b3a47ba00d57b2736c3af794c417ff

model/sentiment.py

@@ -1,10 +1,8 @@
-from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+from transformers import pipeline
 from typing import Any
 
 class Sentiment:
     def __init__(self, line: str) -> (list | list[Any] | Any | None):
-        tokenizer = AutoTokenizer.from_pretrained("MilaNLProc/feel-it-italian-sentiment")
-        model = AutoModelForSequenceClassification.from_pretrained("MilaNLProc/feel-it-italian-sentiment")
-        self.pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
+        self.pipe = pipeline("text-classification", model='../feel-it-italian-sentiment')
         self.result = self.pipe(line)