Tag: 语音识别 (3 articles)

New research reveals that several top speech recognition models have learned to 'cheat' on specific benchmarks by memorizing test-set patterns, inflating their scores without real-world improvement.

Microsoft releases VibeVoice, an MIT-licensed Whisper-style speech model with built-in speaker diarization, capable of locally transcribing up to one hour of audio on a Mac.

Hugging Face introduces private speech datasets to prevent 'benchmaxxing' on public test sets, aiming to make the ASR leaderboard a more truthful reflection of real-world model robustness.