---
language:
- "trv"
library_name: transformers
pipeline_tag: automatic-speech-recognition
tags:
- formosanbank
- formosan
- endangered-languages
- speech
- asr
- whisper-small
- tacl
base_model: openai/whisper-small
base_model_relation: finetune
license: cc-by-4.0
metrics:
- wer
- cer
---

# Formosan ASR — Taroko

This is FormosanBank's current general-purpose automatic speech recognition
checkpoint for **Taroko**. It was selected by the lowest normalized
micro word error rate among the completed language-level TACL systems evaluated
on the same frozen all-corpora test partition.

## Model

- Repository: `FormosanBank/formosan-asr-taroko`
- Architecture family: **Whisper Small**
- Training path: **pan-Formosan supervised fine-tuning followed by language adaptation**
- Base model: `openai/whisper-small`
- Parameters are stored in `model.safetensors`

### Training lineage

1. Base checkpoint: `openai/whisper-small`.
2. Supervised pan-Formosan ASR training, then adaptation to the target language's pooled training corpora.

The target-language supervised stage used `ILRDF`, `ePark1`, `ePark2`, `ePark3`. The experiment used
`dataset_v1`, frozen `split_v2`, normalization `formosan_safe_v1`, and seed
`13`. Full machine-readable provenance is included in
`training_config.json`.

## Evaluation

Evaluation uses the frozen, leakage-controlled `split_v2` test manifests and
normalized text. Metrics are computed by summing edit counts across all
available Taroko test corpora, so larger corpora contribute in
proportion to their reference tokens.

- Normalized micro WER: **6.05%**
- Normalized micro CER: **2.58%**
- Test utterances: **962**
- Test corpora: **4**
- Automated readiness: **pass**

| Corpus | Utterances | WER | CER |
|---|---:|---:|---:|
| ILRDF | 474 | 8.37% | 2.70% |
| ePark1 | 125 | 9.05% | 4.69% |
| ePark2 | 58 | 4.33% | 7.34% |
| ePark3 | 305 | 3.83% | 1.36% |

Detailed edit counts are provided in `evaluation_results.json` and
`metrics_by_corpus.tsv`.

These figures are specific to the frozen TACL evaluation protocol. They should
not be compared directly with the April 2026 stage-one releases, which used a
different experiment snapshot.

## Usage

```python
from transformers import pipeline

repo_id = "FormosanBank/formosan-asr-taroko"
transcribe = pipeline("automatic-speech-recognition", model=repo_id)
result = transcribe("path/to/16khz_audio.wav")
print(result["text"])
```

For long recordings, segment the audio before inference. The training recipe
used utterances between 2 and 20 seconds.

## Intended use

This checkpoint supports research, education, language documentation, and
revitalization work involving Taroko. Human review is recommended
before using transcriptions in archives, publications, teaching materials, or
other consequential settings.

## Limitations

Performance varies substantially across corpora, speakers, recording
conditions, dialects, speaking styles, and orthographic conventions. The
aggregate score can hide weak performance on a particular corpus. The model
may omit, substitute, or hallucinate words and should not be treated as an
authoritative transcription source.

## Data provenance

Training and evaluation artifacts come from the frozen Hunter Formosan TACL
pipeline. Source corpus IDs can include Bible, ILRDF, NTU, ePark1, ePark2,
ePark3, Xuan, YeddaPalemeqBlog, Youtube, and YutasWilang, depending on language
availability. Audio is not redistributed in this repository. Underlying
recordings retain their original rights and access conditions.

## License and attribution

This model release and FormosanBank annotations/metadata are provided under
**CC BY 4.0**. The upstream `openai/whisper-small` checkpoint is distributed under
Apache 2.0. Users remain responsible for respecting the terms associated with
underlying source recordings.

Please cite FormosanBank:

```bibtex
@misc{mohamed2024formosanbank,
  author = {Mohamed, W. and Le Ferrand, É. and Sung, L.-M. and Prud'hommeaux, E. and Hartshorne, J. K.},
  title = {FormosanBank},
  year = {2024},
  note = {Electronic Resource},
  url = {https://ai4commsci.gitbook.io/formosanbank}
}
```