Automatic Speech Recognition
Transformers
Safetensors
Fanti
wav2vec2-bert
speech
asr
african-languages
w2v-bert
khaya
Eval Results (legacy)
Instructions to use KhayaAI/w2v-bert-fat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KhayaAI/w2v-bert-fat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="KhayaAI/w2v-bert-fat")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("KhayaAI/w2v-bert-fat") model = AutoModelForCTC.from_pretrained("KhayaAI/w2v-bert-fat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,11 +25,12 @@ model-index:
|
|
| 25 |
name: WER
|
| 26 |
---
|
| 27 |
|
|
|
|
| 28 |
|
| 29 |
# w2v-bert-fat — Fante (Akan) ASR
|
| 30 |
|
| 31 |
|
| 32 |
-
**DONDO** (
|
| 33 |
Fine-tuned from the **w2v-BERT 2.0** self-supervised speech encoder.
|
| 34 |
|
| 35 |
|
|
@@ -139,7 +140,7 @@ see Khaya Studio.
|
|
| 139 |
author = {{Khaya AI}},
|
| 140 |
year = {2026},
|
| 141 |
institution = {Khaya AI},
|
| 142 |
-
note = {
|
| 143 |
}
|
| 144 |
```
|
| 145 |
|
|
|
|
| 25 |
name: WER
|
| 26 |
---
|
| 27 |
|
| 28 |
+

|
| 29 |
|
| 30 |
# w2v-bert-fat — Fante (Akan) ASR
|
| 31 |
|
| 32 |
|
| 33 |
+
**DONDO** (Democratizing Oral Neural Dialect Ontology) open speech-recognition base model for **Fante (Akan)** (Ghana).
|
| 34 |
Fine-tuned from the **w2v-BERT 2.0** self-supervised speech encoder.
|
| 35 |
|
| 36 |
|
|
|
|
| 140 |
author = {{Khaya AI}},
|
| 141 |
year = {2026},
|
| 142 |
institution = {Khaya AI},
|
| 143 |
+
note = {Democratizing Oral Neural Dialect Ontology. Funded by the Huniki Federation. https://huggingface.co/KhayaAI}
|
| 144 |
}
|
| 145 |
```
|
| 146 |
|