### Evaluation Metric: Word Error Rate (WER)

The primary evaluation metric for this competition is **Word Error Rate (WER)**, a widely used measure in Automatic Speech Recognition (ASR) to assess the accuracy of transcriptions. WER calculates the difference between the transcribed output of the model and the ground-truth text, providing a straightforward way to quantify transcription accuracy.

#### What is Word Error Rate?
WER is calculated by comparing the predicted words with the actual words in the reference transcription. It accounts for three types of errors:

- **Substitutions**: A word is replaced by a different word.
- **Insertions**: An extra word is added in the transcription.
- **Deletions**: A word from the reference is missing in the transcription.

WER is calculated with the following formula:

$$
\text{WER} = \frac{\text{Substitutions} + \text{Insertions} + \text{Deletions}}{\text{Total Words in Reference}}
$$

The resulting score represents the proportion of words that were incorrect in the transcription. A lower WER score indicates better performance, as it implies fewer errors.

#### Why Use WER for Wolof ASR?
WER is particularly useful in this context because it directly reflects the ability of the ASR model to capture the nuances of spoken Wolof, a low-resource language. Given the limited dataset and hardware constraints, optimizing for WER will encourage participants to develop models that handle linguistic variations and speech patterns in Wolof effectively, even with minimal data.

---


## Submission File
For each ID in the test set, you must predict a sentence in wolof for the TARGET variable. The file should contain a header and have the following format:

    row_id,text
    2,bàyyileen gii Maryiis saañaa ak i ñoñam ci nim gën a gaawe !
    5,ku wax ñu ni la ràpp , tëj ci kaso bi !
    6,keneen xool ko  ne kii yëngootul !
    etc.