balaji1312/whisper-medium-swbd-gclora

Whisper-medium Switchboard (GC-LoRA)

Whisper-medium adapted to the Switchboard dataset with GC-LoRA (Gated Convolutional LoRA), from the paper "GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation" (Interspeech 2026).

• —Base model: openai/whisper-medium.en
• —Method: GC-LoRA adapter on the encoder attention output projections (rank 8, kernel 31, scaling 16)
• —Switchboard test WER: 6.3%
• —Code: https://github.com/balaji1312/gc_lora

Usage

The checkpoint bundles the frozen Whisper backbone together with the trained GC-LoRA adapter. Loading requires the custom modeling code in the gc_lora repository; see src/bin/decode_asr.py there for loading and decoding.

Citation

@inproceedings{shankar2026gclora,
  author    = {Shankar, Natarajan Balaji and Wang, Zilai and Zhang, Kaiyuan and Shi, Mohan and Alwan, Abeer},
  title     = {{GC-LoRA}: Gated Convolutional {LoRA} for Parameter-Efficient Acoustic Adaptation},
  booktitle = {Interspeech 2026},
  year      = {2026},
}