Fix HuggingFace token PermissionError when loading embedding model

Pass token=False to SentenceTransformer to skip reading the token file
at /root/.cache/huggingface/token, which fails with a PermissionError
in Docker. The all-MiniLM-L6-v2 model is public and needs no auth.

Author: patrick91

backend/reviews/similar_talks.py

@@ -219,7 +219,7 @@ def get_stopwords_for_languages(language_codes: set[str]) -> set[str]:
 @functools.cache
 def get_embedding_model():
     """Get or create the shared embedding model instance."""
-    return SentenceTransformer("all-MiniLM-L6-v2")
+    return SentenceTransformer("all-MiniLM-L6-v2", token=False)
 
 
 def get_embedding_text(submission) -> str: