Aller au contenu
ModelVérifiéExterne
Télécharger

Whisper Medium Coraal Gclora

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

Sourcehuggingface.co/balaji1312/whisper-medium-coraal-gclora/tree/7b26bbd0aa7da34ee868b184768b5e5e4f583bc5
TypeCheckpointVersionRevision 7b26bbdÉditeur@balaji1312CClasse

Source du modèle

Type
Checkpoint, LoRA
Taille du fichier
2,85 GB
Version
vRevision 7b26bbd
Mis à jour
3 oct. 2026
Éditeur
@balaji1312
Téléchargements
11
Source
Hugging Face

Description de la source

Whisper-medium CORAAL (GC-LoRA)

Whisper-medium adapted to the CORAAL 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)
  • CORAAL test WER: 9.9%
  • 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},
}

Sources

1 source
Hugging FacePrincipalVersion 7b26bbd0aa7da34ee868b184768b5e5e4f583bc5
huggingface.co/balaji1312/whisper-medium-coraal-gclora/tree/7b26bbd0aa7da34ee868b184768b5e5e4f583bc5

Vérifié 3 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 2,85 GB · SHA-256 4255874638f2…fb63 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/balaji1312/whisper-medium-coraal-gclora

--- license: apache-2.0 language: en library_name: transformers pipeline_tag: automatic-speech-recognition tags: - whisper - automatic-speech-recognition - peft - lora - gc-lora - coraal --- # Whisper-medium CORAAL (GC-LoRA) Whisper-medium adapted to the **CORAAL** 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) - **CORAAL test WER:** **9.9%** - **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}, } ```

Note3 oct.huggingface.co/balaji1312/whisper-medium-coraal-gclora

Source context: 11 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo balaji1312/whisper-medium-coraal-gclora

Note17 juil.huggingface.co/balaji1312/whisper-medium-coraal-gclora

Source context: 1 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo balaji1312/whisper-medium-coraal-gclora