Automatic Speech Recognition
Transformers
Safetensors
Lingala
whisper
african-languages
waxal
waxalnet
Instructions to use waxal-benchmarking/whisper-tiny-waxal-lin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use waxal-benchmarking/whisper-tiny-waxal-lin with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="waxal-benchmarking/whisper-tiny-waxal-lin")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("waxal-benchmarking/whisper-tiny-waxal-lin") model = AutoModelForSpeechSeq2Seq.from_pretrained("waxal-benchmarking/whisper-tiny-waxal-lin") - Notebooks
- Google Colab
- Kaggle
Add comprehensive model card (WAXALNet benchmark)
Browse files
README.md
CHANGED
|
@@ -96,42 +96,6 @@ The following hyperparameters were used during training:
|
|
| 96 |
- Datasets 4.0.0
|
| 97 |
- Tokenizers 0.22.2
|
| 98 |
|
| 99 |
-
|
| 100 |
-
## Citation
|
| 101 |
-
|
| 102 |
-
```bibtex
|
| 103 |
-
@article{waxalnet2026,
|
| 104 |
-
title = {The WAXAL ASR Benchmark: Fine-Tuned Edge Models Across 19 African Languages},
|
| 105 |
-
author = {Olufemi, Victor Tolulope and Babatunde, Oreoluwa and Njema, Ramsey and
|
| 106 |
-
Gbotemi, Bolarinwa and Yen, Wanchi Lucia and Uzodinma, John and
|
| 107 |
-
Ajayi, Sunday and Williams, Oluwademilade and Moshood, Kausar and
|
| 108 |
-
Anyaele, Innocent Elendu and Arefaine, Akebert Tesfahunegn and
|
| 109 |
-
Hunzwi, Candace and Daniel, Wongel Dawit and Namuganga, Emmilly Immaculate and
|
| 110 |
-
Kadima, Cleophas and Bahizire, Athanase Biluge and Ranaivoson, Onitsiky and
|
| 111 |
-
Aaron, Emmanuel and Ladislaus, Nicholaus Dismas and Muhammed, Idris and
|
| 112 |
-
Simenya, Jonathan Enoch and Koome, Martin and Endaylalu, Matewos Tegete and
|
| 113 |
-
Adeyemo, Peter Ifeoluwa and Birindwa, Hondi Prisca and Eze-Mbey, Ukachi Agnes and
|
| 114 |
-
Oduro-Yeboah, Yacoba and Aremu, Toluwani and Adjovi, Pericles and
|
| 115 |
-
Ngueajio, Mikel K and Mitra, Prasenjit},
|
| 116 |
-
year = {2026},
|
| 117 |
-
note = {Preprint coming soon}
|
| 118 |
-
}
|
| 119 |
-
```
|
| 120 |
-
|
| 121 |
-
## Authors
|
| 122 |
-
|
| 123 |
-
Victor Tolulope Olufemi 路 Oreoluwa Babatunde 路 Ramsey Njema 路 Bolarinwa Gbotemi 路 Wanchi Lucia Yen 路 John Uzodinma 路 Sunday Ajayi 路 Oluwademilade Williams 路 Kausar Moshood 路 Innocent Elendu Anyaele 路 Akebert Tesfahunegn Arefaine 路 Candace Hunzwi 路 Wongel Dawit Daniel 路 Emmilly Immaculate Namuganga 路 Cleophas Kadima 路 Athanase Biluge Bahizire 路 Onitsiky Ranaivoson 路 Emmanuel Aaron 路 Nicholaus Dismas Ladislaus 路 Idris Muhammed 路 Jonathan Enoch Simenya 路 Martin Koome 路 Matewos Tegete Endaylalu 路 Peter Ifeoluwa Adeyemo 路 Hondi Prisca Birindwa 路 Ukachi Agnes Eze-Mbey 路 Yacoba Oduro-Yeboah 路 Toluwani Aremu 路 Pericles Adjovi 路 Mikel K Ngueajio 路 Prasenjit Mitra
|
| 124 |
-
|
| 125 |
-
## Acknowledgements
|
| 126 |
-
|
| 127 |
-
We thank the following contributors for their language expertise and native-speaker evaluation support:
|
| 128 |
-
Ajara Oyinloye, Abubakari Sadic Mohammed, Hafiz Adjei, Aliga Norah Lele, Marie-Louise B. Ndamuso, and Odong Diana.
|
| 129 |
-
|
| 130 |
-
This work was supported by **[Lynguallabs](https://lynguallabs.org/)** (compute, researchers & storage),
|
| 131 |
-
**[Open Token](https://opentoken.global/)** (compute resources), and
|
| 132 |
-
**[CMU Africa](https://www.africa.engineering.cmu.edu/)** (researchers & native speakers).
|
| 133 |
-
|
| 134 |
-
|
| 135 |
## Citation
|
| 136 |
|
| 137 |
```bibtex
|
|
|
|
| 96 |
- Datasets 4.0.0
|
| 97 |
- Tokenizers 0.22.2
|
| 98 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
## Citation
|
| 100 |
|
| 101 |
```bibtex
|