Whisper Small fine-tuned on WAXAL — Akan
This model is part of WAXALNet, a suite of ASR models fine-tuned on the WAXAL corpus across 19 African languages, developed as part of the WAXAL ASR Benchmark study.
Model Details
| Language | Akan (aka) |
| Language Family | Niger-Congo |
| Architecture | Whisper Small (244M parameters) |
| Base Model | openai/whisper-small |
| Training Data | WAXAL corpus (conversational spontaneous speech) |
| Test WER | 31.7% |
| Test CER | 11.3% |
| License | apache-2.0 |
Intended Use
This model is intended for automatic speech recognition of Akan conversational speech. It was evaluated on the WAXAL test set (spontaneous, image-prompted speech) and partially on FLEURS (read speech). It is suitable for research and low-resource ASR applications. It is not recommended for high-stakes production use without further validation.
Training Data
Fine-tuned on the WAXAL corpus, a large-scale dataset of transcribed, image-prompted spontaneous speech across 19 African languages recorded in participants' natural environments. The Akan training split contains conversational speech across diverse speakers. Data is released under CC-BY 4.0.
Usage
from transformers import pipeline
asr = pipeline("automatic-speech-recognition",
model="waxal-benchmarking/whisper-small-waxal-aka")
result = asr("audio.wav")
print(result["text"])
Test Set Performance (WAXAL Benchmark)
Evaluated on the filtered WAXAL test set (duration >= 1.5s, speech rate >= 4 WPS).
| Metric | Score |
|---|---|
| WER | 31.7% |
| CER | 11.3% |
Full benchmark results across all 19 languages and 6 models are reported in the WAXAL ASR Benchmark paper (citation below).
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.8006 | 1.5823 | 500 | 0.4498 | 0.3172 | 0.1125 |
| 0.4065 | 3.1646 | 1000 | 0.4193 | 0.3014 | 0.1060 |
| 0.3270 | 4.7468 | 1500 | 0.4490 | 0.3158 | 0.1112 |
| 0.1326 | 6.3291 | 2000 | 0.5348 | 0.3101 | 0.1097 |
| 0.1011 | 7.9114 | 2500 | 0.5608 | 0.3191 | 0.1120 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
Citation
@article{waxalnet2026,
title = {The WAXAL ASR Benchmark: Fine-Tuned Edge Models Across 19 African Languages},
author = {Olufemi, Victor Tolulope and Babatunde, Oreoluwa and Njema, Ramsey and
Gbotemi, Bolarinwa and Yen, Wanchi Lucia and Uzodinma, John and
Ajayi, Sunday and Williams, Oluwademilade and Moshood, Kausar and
Anyaele, Innocent Elendu and Arefaine, Akebert Tesfahunegn and
Hunzwi, Candace and Daniel, Wongel Dawit and Namuganga, Emmilly Immaculate and
Kadima, Cleophas and Bahizire, Athanase Biluge and Ranaivoson, Onitsiky and
Aaron, Emmanuel and Ladislaus, Nicholaus Dismas and Muhammed, Idris and
Simenya, Jonathan Enoch and Koome, Martin and Endaylalu, Matewos Tegete and
Adeyemo, Peter Ifeoluwa and Birindwa, Hondi Prisca and Eze-Mbey, Ukachi Agnes and
Oduro-Yeboah, Yacoba and Aremu, Toluwani and Adjovi, Pericles and
Ngueajio, Mikel K and Mitra, Prasenjit},
year = {2026},
note = {arXiv preprint arXiv:2606.02375}
}
Authors
Victor Tolulope Olufemi · Oreoluwa Babatunde · Ramsey Njema · Bolarinwa Gbotemi · Wanchi Lucia Yen · John Uzodinma · Sunday Ajayi · Oluwademilade Williams · Kausar Moshood · Innocent Elendu Anyaele · Akebert Tesfahunegn Arefaine · Candace Hunzwi · Wongel Dawit Daniel · Emmilly Immaculate Namuganga · Cleophas Kadima · Athanase Biluge Bahizire · Onitsiky Ranaivoson · Emmanuel Aaron · Nicholaus Dismas Ladislaus · Idris Muhammed · Jonathan Enoch Simenya · Martin Koome · Matewos Tegete Endaylalu · Peter Ifeoluwa Adeyemo · Hondi Prisca Birindwa · Ukachi Agnes Eze-Mbey · Yacoba Oduro-Yeboah · Toluwani Aremu · Pericles Adjovi · Mikel K Ngueajio · Prasenjit Mitra
Acknowledgements
We thank the following contributors for their language expertise and native-speaker evaluation support: Ajara Oyinloye, Abubakari Sadic Mohammed, Hafiz Adjei, Aliga Norah Lele, Marie-Louise B. Ndamuso, and Odong Diana.
This work was supported by Lynguallabs (compute, researchers & storage), Open Token (compute resources), and CMU Africa (researchers & native speakers).