X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Open paper
Benchmark
Model
Rank
Results
speech-recognition-on-librispeech-test-clean
X-AuT Prune-14 S2
#103
Word Error Rate (WER): 2.45
speech-recognition-on-librispeech-test-other
X-AuT Prune-14 S2
#103
Word Error Rate (WER): 5.52
Rank counts only results with a code link.