Update README.md
Browse files
README.md
CHANGED
@@ -29,6 +29,8 @@ It achieves the following results on the evaluation set:
|
|
29 |
- Accuracy: 0.9747
|
30 |
- F1: 0.9746
|
31 |
|
|
|
|
|
32 |
## Model description
|
33 |
|
34 |
More information needed
|
@@ -38,7 +40,7 @@ More information needed
|
|
38 |
More information needed
|
39 |
|
40 |
## Training and evaluation data
|
41 |
-
```
|
42 |
# datasets for each lang-id
|
43 |
common_voice_train_uz = load_dataset("mozilla-foundation/common_voice_16_1", "uz", split='train', trust_remote_code=True, token=env('HUGGING_TOKEN'), streaming=True)
|
44 |
common_voice_train_ru = load_dataset("mozilla-foundation/common_voice_16_1", "ru", split='train', trust_remote_code=True, token=env('HUGGING_TOKEN'), streaming=True)
|
|
|
29 |
- Accuracy: 0.9747
|
30 |
- F1: 0.9746
|
31 |
|
32 |
+
Accuracy on the test dataset: 92.4%.
|
33 |
+
|
34 |
## Model description
|
35 |
|
36 |
More information needed
|
|
|
40 |
More information needed
|
41 |
|
42 |
## Training and evaluation data
|
43 |
+
```python
|
44 |
# datasets for each lang-id
|
45 |
common_voice_train_uz = load_dataset("mozilla-foundation/common_voice_16_1", "uz", split='train', trust_remote_code=True, token=env('HUGGING_TOKEN'), streaming=True)
|
46 |
common_voice_train_ru = load_dataset("mozilla-foundation/common_voice_16_1", "ru", split='train', trust_remote_code=True, token=env('HUGGING_TOKEN'), streaming=True)
|