Update README.md

README.md

@@ -16,25 +16,37 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-xls-r-300m-hebrew
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the private datasets in 2 stages - firstly was fine-tuned on a small dataset with good samples and it achieves the following results on the evaluation set with the dataset:
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the private datasets in 2 stages - firstly was fine-tuned on a small dataset with good samples Then the obtained model was fine-tuned on a large dataset with the small good dataset, with various samples from different sources, and with an unlabeled dataset that was weakly labeled using a previously trained model.
 
+Small dataset:
 
 | split  |size(gb) | n_samples | duration(hrs)|   |
 |---|---|---|---|---|
 |train|4.19| 20306  | 28  |   |
 |dev  |1.05|  5076 |  7 |   |
 
+Large dataset: 
+
+| split  |size(gb) | n_samples | duration(hrs)|   |
+|---|---|---|---|---|
+|train|12.3| 90777  | 69  |   |
+|dev  |1.05|  20246 |  14* |   |
+(*weakly labeled data wasn't used in validation set)
+
+After firts training it achieves:
+
+on small dataset
 - Loss: 0.5438
 - WER: 0.1773
 
-and on a large dataset
+on large dataset
 - WER: 0.3811
 
-Then the obtained model was fine-tuned on a large dataset with the small good dataset, with various samples from different sources, and with an unlabeled dataset that was weakly labeled using a previously trained model.
-on a small dataset from previous step achieves 
+after second training:
+on small dataset
 - WER: 0.1697
 
-on a whole dataset
+on large dataset
 - Loss: 0.4502
 - WER: 0.2318