Update README.md

README.md

@@ -1,15 +1,13 @@
 ## Description
 
-Afroscope is a MODEL_TYPE (e.g., FastText / Transformer) language identification (LID) model that supports more than N_LABELS labels.
+Afroscope is a language identification (LID) model fine-tuned on [Serengeti](https://huggingface.co/UBC-NLP/serengeti) that supports 713 African Languages.
 
-**Latest:** MODEL_NAME is now updated to VERSION. VERSION supports N_LABELS labels (LABEL_FORMAT_HERE).
 
 For more details on the supported languages and performance, as well as significant changes from previous versions, please refer to LINK_HERE.
 
-- **Demo:** huggingface
-- **Repository:** github
-- **Paper:** paper (VENUE YEAR)
-- **Point of Contact:** EMAIL@DOMAIN.COM
+- **Dataset:** [dataset](https://huggingface.co/datasets/14kwonss/afroscope-data)
+- **Repository:** [github](https://github.com/skwon01-UBC/AfroScope?tab=readme-ov-file)
+- **Paper:** [Arxiv]([VENUE YEAR](https://www.arxiv.org/pdf/2601.13346))
 
 ---
 
@@ -18,14 +16,21 @@ For more details on the supported languages and performance, as well as signific
 Here is how to use this model to detect the language of a given text:
 
 ```python
-import fasttext
-from huggingface_hub import hf_hub_download
+from transformers import pipeline
 
-# model.bin is the latest version always
-model_path = hf_hub_download(repo_id="ORG_OR_USER/MODEL_NAME", filename="model.bin")
 
-model = fasttext.load_model(model_path)
-model.predict("Hello, world!")
+afroscope_model = pipeline("text-classification", model='14kwonss/afroscope-model')
+
+input_text="Ninyepuní íne εtɩε, bε ewǐe Jesi ɔnʋ lεfε kʋkʋkpɔ cε."
+
+result = afroscope_model(input_text)
+
+# Extract the label and score from the first result
+language = result[0]['label']
+score = result[0]['score']
+
+print(f"detected langauge: {language}\tscore: {round(score*100, 2)}")
+
 ```
 
 ## Citation