radiogroup-crits
commited on
Commit
•
ee8c6ec
1
Parent(s):
293f84b
Update README.md
Browse files
README.md
CHANGED
@@ -41,18 +41,16 @@ Our language model was generated using a dataset of Italian wikipedia articles a
|
|
41 |
|
42 |
## Download CommonVoice8.0 dataset for italian language
|
43 |
|
44 |
-
```python
|
45 |
from datasets import load_dataset
|
46 |
|
47 |
dataset = load_dataset("mozilla-foundation/common_voice_8_0", "it", use_auth_token=True)
|
48 |
-
|
49 |
|
50 |
## Evaluation Commands
|
51 |
|
52 |
-
To evaluate on `mozilla-foundation/common_voice_8_0` with split `test
|
53 |
|
54 |
-
```bash
|
55 |
python eval.py --model_id radiogroup-crits/wav2vec2-xls-r-1b-italian-doc4lm-5gram --dataset mozilla-foundation/common_voice_8_0 --config it --split test --log_outputs --greedy
|
56 |
mv log_mozilla-foundation_common_voice_8_0_it_test_predictions.txt log_mozilla-foundation_common_voice_8_0_it_test_predictions_greedy.txt
|
57 |
mv mozilla-foundation_common_voice_8_0_it_test_eval_results.txt mozilla-foundation_common_voice_8_0_it_test_eval_results_greedy.txt
|
58 |
-
|
|
|
41 |
|
42 |
## Download CommonVoice8.0 dataset for italian language
|
43 |
|
|
|
44 |
from datasets import load_dataset
|
45 |
|
46 |
dataset = load_dataset("mozilla-foundation/common_voice_8_0", "it", use_auth_token=True)
|
47 |
+
|
48 |
|
49 |
## Evaluation Commands
|
50 |
|
51 |
+
To evaluate on `mozilla-foundation/common_voice_8_0` with split `test`:
|
52 |
|
|
|
53 |
python eval.py --model_id radiogroup-crits/wav2vec2-xls-r-1b-italian-doc4lm-5gram --dataset mozilla-foundation/common_voice_8_0 --config it --split test --log_outputs --greedy
|
54 |
mv log_mozilla-foundation_common_voice_8_0_it_test_predictions.txt log_mozilla-foundation_common_voice_8_0_it_test_predictions_greedy.txt
|
55 |
mv mozilla-foundation_common_voice_8_0_it_test_eval_results.txt mozilla-foundation_common_voice_8_0_it_test_eval_results_greedy.txt
|
56 |
+
|