Hi, https://docs.mlcommons.org/inference/benchmarks/speech_to_text/get-whisper-data/ mentions that this will download the "validation and calibration datasets and do the necessary preprocessing", but it's not obvious to me which part of this is meant to be used for calibration. My data directory contains: ``` LibriSpeech dev-all dev-all-repack dev-all-repack.json dev-all.json whisper-dataset.md5 ``` Any pointers are very appreciated!
Hi,
https://docs.mlcommons.org/inference/benchmarks/speech_to_text/get-whisper-data/ mentions that this will download the "validation and calibration datasets and do the necessary preprocessing", but it's not obvious to me which part of this is meant to be used for calibration.
My data directory contains:
Any pointers are very appreciated!