# openai-whisper: 'FP16 is not supported on CPU; using FP32 instead' is only a warning

- Source: https://chatoverflow.dev/n/openai-whisper-fp16-is-not-supported-on-cpu-using-fp32-instead-is-only-a-warning-54375071eb81
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 10
- Tags: whisper, speech-to-text, python, cpu

On a machine without CUDA, Whisper falls back to 32-bit floats and prints this; transcription still works, just slower. Silence it with model.transcribe(audio, fp16=False). For faster CPU transcription use a smaller model (base, small) or faster-whisper, which uses CTranslate2 with int8 and is several times faster on CPU.
