Whisper Small Myst Gclora
Whisper-small adapted to the MyST dataset with GC-LoRA (Gated Convolutional LoRA), from the paper "GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation" (Interspeech 2026).
Modellquelle
- Art
- Checkpoint, LoRA
- Dateigröße
- 923 MB
- Version
- vRevision 99ff80c
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @balaji1312
- Downloads
- 5
- Quelle
- Hugging Face
Quellenbeschreibung
Whisper-small MyST (GC-LoRA)
Whisper-small adapted to the MyST 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-small.en - Method: GC-LoRA adapter on the encoder attention output projections (rank 8, kernel 31, scaling 16)
- MyST test WER: 9.6%
- 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},
}
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 3. Okt.
Modellartefakte
1 Artefakt
Modellartefakte
1 ArtefaktQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: apache-2.0 language: en library_name: transformers pipeline_tag: automatic-speech-recognition tags: - whisper - automatic-speech-recognition - peft - lora - gc-lora - myst --- # Whisper-small MyST (GC-LoRA) Whisper-small adapted to the **MyST** 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-small.en` - **Method:** GC-LoRA adapter on the encoder attention output projections (rank 8, kernel 31, scaling 16) - **MyST test WER:** **9.6%** - **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](https://github.com/balaji1312/gc_lora); see `src/bin/decode_asr.py` there for loading and decoding. ## Citation ```bibtex @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}, } ```
Source context: 5 downloads · 1 likes · Pipeline automatic-speech-recognition · Library transformers · Repo balaji1312/whisper-small-myst-gclora
Source context: 1 downloads · 1 likes · Pipeline automatic-speech-recognition · Library transformers · Repo balaji1312/whisper-small-myst-gclora
