Predictions in phase1 are evaluated by [Levenshtein Mean Distance](https://en.wikipedia.org/wiki/Levenshtein_distance) between the predicted sentence and the ground truth sentence. The Levenshtein distance between two sentences is the minimum number of single-character edits (insertions, deletions, or substitutions) required to change one sentence into the other

The Levenshtein Distance between two strings *a, b* having length |a| and |b| correspondingly is given by *lev(a, b)*
![Levenshtein Distance](https://wikimedia.org/api/rest_v1/media/math/render/svg/6224efffbe9a4e01afbddeeb900bfd1b3350b335)

Now, Levenshetin Mean for **n** samples, where **gt[i]** and **pred[i]** indicates ground truth and prediction of sample **i**, is calculated by,

$$levenshteinMean=\frac{\sum_{i=1}^{n} lev\(gt\[i\], pred\[i\] \)}{n}$$

**Note:** For this competition, we will consider finding Levenshtein Mean among the Unicode token values of ground truth and predicted sentence. 

**All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions and documentations for reproducibility after Phase 1 Part 1.**

## Submission Format


The submission files should contain two columns: `path` and `sentence`.  You will need to predict the sentence for each file in the `test_files` folder. 


The submission file should contain a header and have the following format:
```
path, sentence
common_voice_bn_31675220.mp3, এছাড়াও নিউজিল্যান্ড এ ক্রিকেট দলের হয়েও খেলছেন তিনি।
common_voice_bn_31513116.mp3, এছাড়াও নিউজিল্যান্ড এ ক্রিকেট দলের হয়েও খেলছেন তিনি।
```