Always Prompts Insufficient Video Memory (whole all Unable to allocate)

1. Use a Smaller Model: Change the recognition model from large-v3 to medium, small, or base. The large-v3 model requires at least 10GB of video memory.
2. Try disabling the Secondary Recognition option in the top-right corner of the main interface. This is especially important when translating multiple videos simultaneously, as the secondary recognition of an earlier video may run concurrently with the first transcription of a later video, requiring 2-3 times the video memory. This could cause an error if the available video memory is insufficient.
3. Adjust Advanced Settings: Make the following changes in the menu bar Tools/Options -> Advanced Options to sacrifice some accuracy for lower video memory usage:
   • CUDA Data Type: Change float32 to float16 or int8.
   • beam_size: Change 5 to 1.
   • best_of: Change 5 to 1.
   • Context: Change true to false.