facebook/wav2vec2-large-960h-lv60-self for CTC forced
alignment in the browser (onnxruntime-web, WebGPU EP):input_values [1, samples] float32 @16 kHz (zero-mean/unit-var
normalized host-side)logits [1, frames, 32] — the standard wav2vec2-960h char vocab
(<pad>=0 = CTC blank, |=4 word separator, A–Z + ')eval/export-large-align.py in the
KaraokeVideoEditor repo.