Base model download requires more than 13GB of space

[PricelessToolkit]

Hi,

I attempted to run the following command using the base model:

docker run -d --gpus all -p 9000:9000 -e ASR_MODEL=base -e ASR_ENGINE=openai_whisper onerahmet/openai-whisper-asr-webservice:latest-gpu

However, I found that 13GB of available space on my SSD was insufficient. Is the container downloading additional models beyond the base model, or is there something else contributing to the large storage requirement? and how I can select the precision int8

Thank you!

[ayancey]

CUDA binaries are pretty large too.