FP16 is not supported on CPU; using FP32 instead

3 min read

venv/lib/python3.10/site-packages/whisper/transcribe.py:114: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")

This warning message indicates that the code is attempting to use 16-bit floating point precision (FP16) on a CPU that does not support it. As a result, the code will use 32-bit floating point precision (FP32) instead. This may have implications on the accuracy and speed of the computation, but in most cases, the difference may be negligible.