---
library_name: transformers
pipeline_tag: automatic-speech-recognition
language:
- en
base_model: openai/whisper-small
tags:
- automatic-speech-recognition
- whisper
- child-speech
- model-merging
- compositional-domain-adaptation
- 05_cross_corpus_small
- supervised-fine-tuning
---

# Whisper Small SFT: AMI

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:** Cross-corpus transfer
- **Checkpoint kind:** Single-source supervised fine-tuned checkpoint
- **Manuscript role:** Adult conversational cross-corpus source model
- **Source artifact:** `05_cross_corpus_small/whisper_small_train`

## Method Context

This is a single-source fine-tuned checkpoint. In the manuscript it serves as a source model, baseline, or task-vector endpoint for studying how distribution-shift factors can be recombined.

Training/adaptation context: Cross-corpus transfer from adult conversational speech.

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

```python
from transformers import WhisperForConditionalGeneration, WhisperProcessor

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

For local use before upload:

```python
from pathlib import Path
from transformers import WhisperForConditionalGeneration, WhisperProcessor

model_dir = Path("final_release_models") / "05_cross_corpus_small" / "whisper_small_sft_ami"
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, tokenizer.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:

```bibtex
@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}
}
```