accuracy changes
Browse files
README.md
CHANGED
@@ -24,10 +24,10 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Test WER
|
26 |
type: wer
|
27 |
-
value:
|
28 |
- name: Validation WER
|
29 |
type: wer
|
30 |
-
value: 36.
|
31 |
---
|
32 |
# Wav2Vec2-Large-XLSR-53-Arabic
|
33 |
|
@@ -197,9 +197,9 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
|
197 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
198 |
```
|
199 |
|
200 |
-
**Test Result**: 36.
|
201 |
|
202 |
|
203 |
## Future Work
|
204 |
|
205 |
-
One can use *data augmentation*, *transliteration*, or *attention_mask* to increase the accuracy.
|
|
|
24 |
metrics:
|
25 |
- name: Test WER
|
26 |
type: wer
|
27 |
+
value: 36.69
|
28 |
- name: Validation WER
|
29 |
type: wer
|
30 |
+
value: 36.69
|
31 |
---
|
32 |
# Wav2Vec2-Large-XLSR-53-Arabic
|
33 |
|
|
|
197 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
198 |
```
|
199 |
|
200 |
+
**Test Result**: 36.69%
|
201 |
|
202 |
|
203 |
## Future Work
|
204 |
|
205 |
+
One can use *data augmentation*, *transliteration*, or *attention_mask* to increase the accuracy.
|