Update README.md

README.md

@@ -7,10 +7,10 @@ tags:
 - climate
 ---
 
-# CatastroBERT a model for Extreme weather events detection in french text
+# CatastroBERT a model for Extreme weather events detection in French text
 
 This model aims to facilitate the detection of paragraphs or articles relevant to extreme weather events
-in french text. It is based on the [camembert-base](https://huggingface.co/camembert-base) model and was trained on manually anotated data (articles summaries) from the Gazette de Lausanne archives  collected by [impresso](https://impresso-project.ch/)
+in French text. It is based on the [camembert-base](https://huggingface.co/camembert-base) model and was trained on manually annotated data (articles summaries) from the Gazette de Lausanne archives  collected by [impresso](https://impresso-project.ch/)
 
 <div align=center>
     <img src="images/bert_illustration.png" width="500" height="500" />
@@ -22,7 +22,7 @@ in french text. It is based on the [camembert-base](https://huggingface.co/camem
 - **Language(s) (NLP):** French
 - **Finetuned from model :** [camembert-base](https://huggingface.co/camembert-base) (RoBERTa Checkpoint)
 
-- **Repository:** Check the [CatastroBERT](https://github.com/dh-epfl-students/dhlab-CatastroBERT) github page for more usage examples and information.
+- **Repository:** Check the [CatastroBERT](https://github.com/dh-epfl-students/dhlab-CatastroBERT) GitHub page for more usage examples and information.
 
 ## Usage
 
@@ -71,7 +71,7 @@ print(f"Prediction: {predict(text)}")
 
 ### Training Data
 
-This model was trained on manually a manually anotated dataset (articles summaries) curated from the Gazette de Lausanne archives  collected by the [impresso](https://impresso-project.ch/) project. The dataset is composed of 4500 articles summaries of which 3500 were used for training and 1000 for validation.
+This model was trained on manually a manually annotated dataset (articles summaries) curated from the Gazette de Lausanne archives  collected by the [impresso](https://impresso-project.ch/) project. The dataset is composed of 4500 articles summaries of which 3500 were used for training and 1000 for validation.
 
 ## Environmental Impact