balaji1312/whisper_small_hsa_spon_3_5_noise_rir_script_0_2

Whisper Small HSA Merge: noise/RIR Spon 3-5 + Script 0-2

This repository contains a minimal Hugging Face Transformers checkpoint for the manuscript Compositional Domain Adaptation for Automatic Speech Recognition with Headwise Selective Attention Merging.

Model Details

• Model type: Whisper sequence-to-sequence ASR model
• Base model: openai/whisper-small
• Release group: Acoustic robustness
• Checkpoint kind: Headwise Selective Attention (HSA) merged checkpoint
• Manuscript role: Acoustic robustness merge
• Source artifact: 03_robustness_acoustic_small/hsa_merge_noise_rir

Method Context

This is a structured model merge for compositional domain adaptation. It composes task-specific adaptations without additional retraining by restricting parameter arithmetic to salient attention heads where the adaptations are concentrated.

Training/adaptation context: Acoustic robustness composition: noisy/reverberant spontaneous speech and scripted 0-2 adaptations.

The broader manuscript studies whether speech foundation model adaptations for different distribution shifts, such as acoustic condition, speaking style, speaker population, and dialect, can be recombined for low-resource and intersectional ASR without direct joint-supervision data.

Intended Use

Use this checkpoint to reproduce or extend the paper's ASR model-merging experiments. It is intended for research on child ASR, compositional domain adaptation, robustness, cross-corpus transfer, dialectal variation, and scaling behavior across Whisper model sizes.

How To Load

from transformers import WhisperForConditionalGeneration, WhisperProcessor

model_id = "balaji1312/whisper_small_hsa_spon_3_5_noise_rir_script_0_2"
processor = WhisperProcessor.from_pretrained(model_id)
model = WhisperForConditionalGeneration.from_pretrained(model_id)

For local use before upload:

from pathlib import Path
from transformers import WhisperForConditionalGeneration, WhisperProcessor

model_dir = Path("final_release_models") / "03_robustness_acoustic_small" / "whisper_small_hsa_spon_3_5_noise_rir_script_0_2"
processor = WhisperProcessor.from_pretrained(model_dir)
model = WhisperForConditionalGeneration.from_pretrained(model_dir)

Release Files

This model card was generated for the curated release tree. The model-loading payload consists of:

config.json, generation_config.json, preprocessor_config.json, tokenizer_config.json, vocab.json, merges.txt, normalizer.json, special_tokens_map.json, added_tokens.json, model.safetensors

Training state, optimizer state, decode logs, hypotheses, references, and intermediate experiment outputs were intentionally omitted.

Limitations

The checkpoint is released for research reproducibility. Results outside the paper's child ASR, robustness, cross-corpus, dialectal, and scaling-law settings are not characterized here. Reproducing WER numbers requires the manuscript evaluation pipeline and authorized access to the relevant speech corpora; no evaluation audio or transcripts are redistributed in this model folder.

Citation

If you use this checkpoint, please cite the manuscript:

@article{shankara2026compositional,
  title = {Compositional Domain Adaptation for Automatic Speech Recognition with Headwise Selective Attention Merging},
  author = {Shankara, Natarajan Balaji and Wang, Zilai and Eren, Eray and Alwan, Abeer},
  year = {2026},
  note = {Manuscript submitted to Computer Speech & Language}
}