Updated readme file

README.md

@@ -89,8 +89,17 @@ print("Reference:", test_dataset["sentence"][:2])
 ## Evaluation
 
 The model can be evaluated as follows on the following two datasets: 
-1. Custom dataset created from 20% of Indic, IIITH and CV (test): 17. 
-2. CommonVoice Hindi test dataset
+1. Custom dataset created from 20% of Indic, IIITH and CV (test): WER 17.xx% 
+2. CommonVoice Hindi test dataset: WER 56.xx%
+
+Links to the datasets are provided above (check the links at the start of the README)
+
+train-test csv files are shared on the following gdrive links:
+a. IIITH [train](https://storage.googleapis.com/indic-dataset/train_test_splits/iiit_hi_train.csv) [test](https://storage.googleapis.com/indic-dataset/train_test_splits/iiit_hi_test.csv)
+b. Indic TTS [train](https://storage.googleapis.com/indic-dataset/train_test_splits/indic_train_full.csv) [test](https://storage.googleapis.com/indic-dataset/train_test_splits/indic_test_full.csv)
+
+
+Update the audio_path as per the 
 
 ```python
 import torch