Autoregressive Audio Token Generation With Long Term Dependency Modeling

via “variable-length audio sequence processing with automatic padding/truncation”

automatic-speech-recognition model by undefined. 67,92,170 downloads.

Unique: Uses learnable positional embeddings in the encoder that generalize across variable sequence lengths, combined with attention masking for padding — allowing single-pass processing of any audio duration without retraining, unlike fixed-length models that require explicit bucketing

vs others: More efficient than sliding-window approaches (which require overlapping inference) and simpler than hierarchical models that process multiple time scales; attention masking prevents padding artifacts that plague naive padding strategies