Open Sathvik902 opened 1 year ago
@khusheekapoor, Please add @GSSOC tag before merging the request as I am contributing under it. Thank you.
@Sathvik902 - please only start working on an issue after you've been assigned. Failing to follow the rules will result in your contributions not being counted. However, since this is the first instance, we are allowing it. We will merge your PR after reviewing it.
@khusheekapoor , Please add "GssoC'23" label before merging it, as I'm contributing under gssoc. Thank you.
@Sathvik902 - please only start working on an issue after you've been assigned. Failing to follow the rules will result in your contributions not being counted. However, since this is the first instance, we are allowing it. We will merge your PR after reviewing it.
Sure!
💥 Proposal
This is the approach what I am following:
This is a language detection model with detects the language of the text provided. Steps Data processing: 1.Removing the inconsistencies such as capital letters and punctuations from the dataset. Model building: 1.Using pipeline, Convert the text into number format so that the input can be fed into the model. 2.Using TFIDF vectorization method as a second step of the pipeline. 3.Applying Logistic regression and generating the output.
Accuracy can be reached up to 97% percent by using these steps.
After these steps, exporting the model using pickle.
@khusheekapoor , Please assign it to me as a part of @GSSOC'23 Contribution. Thank you.