Update README.md

README.md

@@ -30,8 +30,8 @@ the audiobook of the translation of _Le Petit Prince_ into the Chakavian dialect
 
 ### Model Description
 
-The model was finetuned for 80 epochs with an effective batch size of 16. Performance was inspected every 4 epochs, and the latest checkpoint
-is uploaded here.
+The model, already very potent in standard Croatian, was finetuned for 80 epochs with an effective batch size of 16. Performance was inspected every 4 epochs, and the latest checkpoint
+is uploaded here. Character error rate has been brought down from 11.54% to 3.95%, while word error rate has been lowered from 35.43% to 16.83%.
 
 - **Developed by:** Nikola Ljubešić, Peter Rupnik, Tea Perinčić
 - **Language(s) (NLP):** Croatian (hrv) - Chakavian dialect (ckm)
@@ -121,11 +121,13 @@ Only the `train` split was used in training.
 For evaluation, the `test` split of the [Mići Princ dataset](https://huggingface.co/datasets/classla/Mici_Princ) was used. The test split consists of two known speakers, Autor and Mići Princ, and two unknown speakers, Geograf and Dilavac. Important to note is that each speaker uses a different micro-dialect, so the test data is challenging on including two new micro-dialects.
 
 #### Metrics
-
-
-* WER: 0.039493
-* CER: 0.168341
-
+| speaker | WER vanilla | WER fine-tuned | WER reduction | CER vanilla | CER fine-tuned| CER reduction | 
+|---|---|---|---|---|---|---|
+| all | 35.43% |  16.83% | 52.50% | 11.54% | 3.95% | 65.77% |
+| Autor | 38.96% | 14.29% | 63.32% | 10.24% | 2.93% | 71.39% |
+| Geograf | 20.94% | 11.57% | 44.75% | 4.99% | 2.19% | 56.11% |
+| Mići Princ | 45.31% | 16.62% | 63.32% | 12.21% | 5.09% | 58.31% |
+| Dilavac |  39.60% | 23.70% | 40.15% | 18.55% | 5.27% | 71.59% |
 
 ## Citation