Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
# Language Identifier
|
| 2 |
---
|
| 3 |
|
| 4 |
-
|
| 5 |
This project is a Flask web application that identifies the language of input text. It uses a machine learning model trained on text data to make predictions. The user inputs text into a form on the web app, and the app returns the predicted language.
|
| 6 |
|
| 7 |
-
|
| 8 |
- The data used for training is taken from Kaggle. It has 22 different languages.
|
| 9 |
- The text in the dataset has tokenization, non alphanumeric characters removal and vectorization applied to it.
|
| 10 |
- The model used for training has 4 layers with 27M params which is enough for getting high accuracy. Complex architectures couldn’t be used because of not sufficient GPUs.
|
|
@@ -14,7 +14,7 @@ This project is a Flask web application that identifies the language of input te
|
|
| 14 |
- The project uses Flask, a lightweight web framework for Python, to create the web application.
|
| 15 |
- The input text is preprocessed before being fed into the model for prediction.
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
```python
|
| 20 |
def predict_language(text, model, cv, le):
|
|
|
|
| 1 |
# Language Identifier
|
| 2 |
---
|
| 3 |
|
| 4 |
+
### OVERVIEW
|
| 5 |
This project is a Flask web application that identifies the language of input text. It uses a machine learning model trained on text data to make predictions. The user inputs text into a form on the web app, and the app returns the predicted language.
|
| 6 |
|
| 7 |
+
### SPECIFICATIONS
|
| 8 |
- The data used for training is taken from Kaggle. It has 22 different languages.
|
| 9 |
- The text in the dataset has tokenization, non alphanumeric characters removal and vectorization applied to it.
|
| 10 |
- The model used for training has 4 layers with 27M params which is enough for getting high accuracy. Complex architectures couldn’t be used because of not sufficient GPUs.
|
|
|
|
| 14 |
- The project uses Flask, a lightweight web framework for Python, to create the web application.
|
| 15 |
- The input text is preprocessed before being fed into the model for prediction.
|
| 16 |
|
| 17 |
+
### USAGE
|
| 18 |
|
| 19 |
```python
|
| 20 |
def predict_language(text, model, cv, le):
|