A parameter-efficient adapter bridging Whisper and TinyLlama reports relative improvements in speech recognition, named entity recognition, and sentiment analysis on low-resource benchmarks.
We conduct the SA training for 50 epochs with a learning rate 5 ∗ 10−4, batch size 6, and a linear decay scheduler with 3000 warm-up steps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings
A parameter-efficient adapter bridging Whisper and TinyLlama reports relative improvements in speech recognition, named entity recognition, and sentiment analysis on low-resource benchmarks.