Hi, I’m using a Wav2Vec2 model (Clementapa/wav2vec2-base-960h-phoneme-reco-dutch · Hugging Face) to decode phoneme labels from audio. The purpose is to generate labels for EEG timeseries recorded concurrently, so I need to know the length of the time window that the model operates on. Is there either a way to retrieve this information from the model, somewhere I can look it up, or someone who might be able to tell me?
I would really appreciate any help, complete or partial!
Thanks!