From 896dad5cc92fe1ec011abe2e38caee3e113405c5 Mon Sep 17 00:00:00 2001
From: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
Date: Wed, 9 Oct 2024 13:55:34 -0500
Subject: [PATCH] use trust remote code per transformers docs

---
 frigate/embeddings/functions/onnx.py | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/frigate/embeddings/functions/onnx.py b/frigate/embeddings/functions/onnx.py
index abdac7aef..454fe3faf 100644
--- a/frigate/embeddings/functions/onnx.py
+++ b/frigate/embeddings/functions/onnx.py
@@ -75,6 +75,7 @@ class GenericONNXEmbedding:
                         logger.info(f"Downloading {self.model_name} tokenizer")
                     tokenizer = AutoTokenizer.from_pretrained(
                         self.model_name,
+                        trust_remote_code=True,
                         cache_dir=f"{MODEL_CACHE_DIR}/{self.model_name}/tokenizer",
                         clean_up_tokenization_spaces=True,
                     )
@@ -84,6 +85,7 @@ class GenericONNXEmbedding:
                         logger.info(f"Downloading {self.model_name} feature extractor")
                     feature_extractor = AutoFeatureExtractor.from_pretrained(
                         self.model_name,
+                        trust_remote_code=True,
                         cache_dir=f"{MODEL_CACHE_DIR}/{self.model_name}/feature_extractor",
                     )
                     feature_extractor.save_pretrained(path)
@@ -119,7 +121,10 @@ class GenericONNXEmbedding:
     def _load_tokenizer(self):
         tokenizer_path = os.path.join(f"{MODEL_CACHE_DIR}/{self.model_name}/tokenizer")
         return AutoTokenizer.from_pretrained(
-            self.model_name, cache_dir=tokenizer_path, clean_up_tokenization_spaces=True
+            self.model_name,
+            cache_dir=tokenizer_path,
+            trust_remote_code=True,
+            clean_up_tokenization_spaces=True,
         )
 
     def _load_feature_extractor(self):
@@ -127,7 +132,7 @@ class GenericONNXEmbedding:
             f"{MODEL_CACHE_DIR}/{self.model_name}/feature_extractor"
         )
         return AutoFeatureExtractor.from_pretrained(
-            self.model_name, cache_dir=feature_extractor_path
+            self.model_name, trust_remote_code=True, cache_dir=feature_extractor_path
         )
 
     def _load_model(self, path: str, providers: List[str]):