Whisper

The 'Whisper' dataset/benchmark is used to evaluate automatic speech recognition (ASR) models by comparing decoded utterances against ASR-inferred transcriptions of input speech.

Papers using Whisper (2)

From Hallucination to Articulation: Language Model-Driven Losses for Ultra Low-Bitrate Neural Speech Coding2026Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models2024