Update README.md

README.md

@@ -73,21 +73,20 @@ wer_metric = load("wer")
 | finetune (this model) |    94.837     |      1.429      |      2.951      |       67.659     |      7.951      |      18.313     |
 
 
-### Details
+Evaluation was done on the following datasets:
+- ASR (Automatic Speech Recognition): Evaluated with CER (Character Error Rate) on zeroth-test set (457 samples).
+- AST (Automatic Speech Translation): Evaluated with BLEU score on fleurs ko <-> en speech translation result (270 samples).
 
+Script is retrieved from [here](https://gist.github.com/seastar105/d1d8983b27611370528e3b194dcc5577#file-evaluate-py).
 
-ZerothDataset | BLEU Score after finetuning: 94.8373308036857
-
-ZerothDataset | CER after finetuning: 0.014290201005025125
-
-ZerothDataset | WER after finetuning: 0.02951362746574311
-
-FleursDataset | BLEU Score after finetuning: 67.6597801681411
-
-FleursDataset | CER after finetuning: 0.07951429690560126
-
-FleursDataset | WER after finetuning: 0.183130832893115
+Compared to [Phi-4-mm-inst-zeroth-kor](https://huggingface.co/seastar105/Phi-4-mm-inst-zeroth-kor) and  [Phi-4-multimodal-finetune-ko-speech](https://huggingface.co/daekeun-ml/Phi-4-multimodal-finetune-ko-speech), ASR is significantly improved.
 
+| Model                | zeroth-test | fleurs-ko2en | fleurs-ko2en-cot | fleurs-en2ko | fleurs-en2ko-cot |
+|----------------------|-------------|--------------|------------------|--------------|------------------|
+| original             |  198.32     | 5.63         | 2.42             | 6.86         | 4.17             |
+| finetune (this model)|  1.31       | 7.46         | 6.24             | 12.15        | 8.91             |
+| daekeun-ml/Phi-4-multimodal-finetune-ko-speech|  3.80       | 7.03         | 7.04             | 12.50        | 9.54             |
+| seastar105/Phi-4-mm-inst-zeroth-kor |  7.02       | 7.07         | 9.19             | 13.08        | 9.35             |