spellingdragon
/

whisper-large-v3-handler

Automatic Speech Recognition

hf-asr-leaderboard

Inference Endpoints

Model card Files Files and versions Community

spellingdragon commited on Nov 25, 2023

Commit

28b840e

•

1 Parent(s): d5325ba

Update handler.py

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -11,7 +11,7 @@ class EndpointHandler():
         self.model = AutoModelForSpeechSeq2Seq.from_pretrained(
             model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
         )
-        model.to(device)
         processor = AutoProcessor.from_pretrained(model_id)

         self.model = AutoModelForSpeechSeq2Seq.from_pretrained(
             model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
         )
+        self.model.to(device)
         processor = AutoProcessor.from_pretrained(model_id)