No AI summary available for this article.
Why It Matters
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.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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 {\tt whisper-large-v3-turbo} variant reduced the decoder from 32 to 4 layers, while Distill-Whisper similarly reduced the decoder to only 2 layers. Although some attention has been put towards reducing the size of the encoder, no approach has seen wide adoption. This could be due to the need for custom inference implementations to take advantage of the compressed model. We present an approach that...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.27980v1 · Indexed about 1 hour ago