Automatic Speech Recognition
Transformers
PyTorch
Swahili
wav2vec2
Generated from Trainer
Eval Results (legacy)
Instructions to use Skier8402/wav2vec-xls-r with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skier8402/wav2vec-xls-r with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Skier8402/wav2vec-xls-r")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Skier8402/wav2vec-xls-r") model = AutoModelForCTC.from_pretrained("Skier8402/wav2vec-xls-r", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -37,6 +37,8 @@ It achieves the following results on the evaluation set:
|
|
| 37 |
- Loss: 2.1585
|
| 38 |
- Wer: 0.9982
|
| 39 |
|
|
|
|
|
|
|
| 40 |
## Model description
|
| 41 |
|
| 42 |
More information needed
|
|
|
|
| 37 |
- Loss: 2.1585
|
| 38 |
- Wer: 0.9982
|
| 39 |
|
| 40 |
+
Increase the number of epochs to improve performance or use a bigger model.
|
| 41 |
+
|
| 42 |
## Model description
|
| 43 |
|
| 44 |
More information needed
|