The paper introduces a method to prune six layers from the encoder of OpenAI’s Whisper ASR model, reducing the encoder stack by 18.5% without requiring custom inference code. Layers are selected based on their minimal impact on Word Error Rate when removed. After pruning, the model’s WER rises from 18.2% to 21.9%, but distillation with unlabeled monolingual speech data lowers it to 20.1%. "whyItMatters":"The approach offers a straightforward way to accelerate Whisper inference by simplifying the encoder while maintaining acceptable accuracy, and the released code and model enable immediate adoption by the community."
Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the...
X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.
arXiv:2511.08092v2 Announce Type: replace-cross Abstract: We challenge the conventional view of neural network pruning as solely a compression technique, demonstrating that one-shot magnitude pruning...
arXiv:2603. 05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters.
arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.
arXiv:2509.10452v3 Announce Type: replace-cross Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance....
arXiv:2609.38106v1 Announce Type: cross Abstract: Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggre...
arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
arXiv:2606. 24169v1 Announce Type: new Abstract: Adapting a streaming speech recognition model to a new language requires choosing between two plausible warm starts: a multilingual (ML) encoder or an English-only (EN) encoder.
The paper demonstrates that layer dropout, also known as stochastic depth, can be effectively used in state‑of‑the‑art large language model (LLM) training. By optimizing the layer distribution, schedule, and optimizer settings, the authors show that layer dropout can reduce training loss while saving up to 25 % of training FLOPs. Additionally, layer dropout enables post‑training optimizations such as early exit and self‑speculative decoding, achieving up to 1.5× inference speedup with negligible accuracy loss across models ranging from 271 M to 8.2 B parameters and datasets up to 160 B tokens.
arXiv:2609.06557v1 Announce Type: new Abstract: Large language models (LLMs) are often considered fragile under aggressive sparsification, and maintaining reliable performance typically requires stic...
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.