Aller au contenu
ModelVérifiéExterne
Télécharger

Whisper Medium Ami Gclora

Whisper-medium adapted to the AMI 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-ami-gclora/tree/34f27d14c3c1b9e474eb32d1ba21817676c47bf8
TypeOtherVersionRevision 34f27d1Éditeur@balaji1312CClasse

Source du modèle

Type
Other
Taille du fichier
2,85 GB
Version
vRevision 34f27d1
Mis à jour
23 oct. 2026
Éditeur
@balaji1312
Téléchargements
2
Source
Hugging Face

Description de la source

Whisper-medium AMI (GC-LoRA)

Whisper-medium adapted to the AMI 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)
  • AMI test WER: 11.6%
  • 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},
}

Sources

1 source
Hugging FacePrincipalVersion 34f27d14c3c1b9e474eb32d1ba21817676c47bf8
huggingface.co/balaji1312/whisper-medium-ami-gclora/tree/34f27d14c3c1b9e474eb32d1ba21817676c47bf8

Vérifié 23 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 2,85 GB · SHA-256 09a8fe3ec243…6ef6 · Hugging Face

Download file

Extraits de sources

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

--- license: apache-2.0 language: en library_name: transformers pipeline_tag: automatic-speech-recognition tags: - whisper - automatic-speech-recognition - peft - lora - gc-lora - ami --- # Whisper-medium AMI (GC-LoRA) Whisper-medium adapted to the **AMI** 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) - **AMI test WER:** **11.6%** - **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}, } ```

Note6 aoûthuggingface.co/balaji1312/whisper-medium-ami-gclora

Source context: 3 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo balaji1312/whisper-medium-ami-gclora

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

Source context: 2 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo balaji1312/whisper-medium-ami-gclora