diff --git a/vllm/entrypoints/openai/speech_to_text/speech_to_text.py b/vllm/entrypoints/openai/speech_to_text/speech_to_text.py index 671412921c..4ebc612a41 100644 --- a/vllm/entrypoints/openai/speech_to_text/speech_to_text.py +++ b/vllm/entrypoints/openai/speech_to_text/speech_to_text.py @@ -389,6 +389,9 @@ class OpenAISpeechToText(OpenAIServing): if error_check_ret is not None: return error_check_ret + if not request.model: + request.model = self.models.model_name() + # If the engine is dead, raise the engine's DEAD_ERROR. # This is required for the streaming case, where we return a # success status before we actually start generating text :).