FADE adaptively compensates for quantization errors layer-by-layer in ASR models using diagnostic scores from weight geometry and calibration data, yielding lower word error rates at 3- and 4-bit precision.
SparseGPT: Massive language models can be accurately pruned in one-shot,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models
FADE adaptively compensates for quantization errors layer-by-layer in ASR models using diagnostic scores from weight geometry and calibration data, yielding lower word error rates at 3- and 4-bit precision.