update app.py

app.py

@@ -18,6 +18,7 @@ import altair as alt
 from altair import X, Y, Scale
 import base64
 import json
+import os
 
 @st.cache_resource
 def load_sp():
@@ -71,6 +72,34 @@ def render_svg(svg):
     c.write(html, unsafe_allow_html=True)
 
 
+@st.cache_data
+def render_metadata():
+    """Renders the metadata."""
+    html = r"""<p align="center">
+        <a href="https://huggingface.co/cis-lmu/glotlid"><img alt="HuggingFace Model" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-8A2BE2"></a>
+        <a href="https://github.com/cisnlp/GlotLID"><img alt="GitHub" src="https://img.shields.io/badge/%F0%9F%93%A6%20GitHub-orange"></a>
+        <a href="https://github.com/cisnlp/GlotLID/blob/main/LICENSE"><img alt="GitHub license" src="https://img.shields.io/github/license/cisnlp/GlotLID?logoColor=blue"></a>
+        <a href="."><img alt="GitHub stars" src="https://img.shields.io/github/stars/cisnlp/GlotLID"></a>
+        <a href="https://arxiv.org/abs/2310.16248"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-2310.16248-b31b1b.svg"></a>
+        </p>"""
+    c = st.container()
+    c.write(html, unsafe_allow_html=True)
+
+@st.cache_data
+def citation():
+    """Renders the metadata."""
+    _CITATION  = """
+    @inproceedings{
+      kargaran2023glotlid,
+      title={GlotLID: Language Identification for Low-Resource Languages},
+      author={Kargaran, Amir Hossein and Imani, Ayyoob and Yvon, Fran{\c{c}}ois and Sch{\"u}tze, Hinrich},
+      booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
+      year={2023},
+      url={https://openreview.net/forum?id=dl4e3EBz5j}
+    }"""
+    st.code(_CITATION, language="python", line_numbers=False)
+
+
 @st.cache_data
 def convert_df(df):
     # IMPORTANT: Cache the conversion to prevent computation on every rerun
@@ -93,7 +122,7 @@ def load_GlotLID_v2(model_name, file_name):
 model_1 = load_GlotLID_v1(constants.MODEL_NAME, "model_v1.bin")
 model_2 = load_GlotLID_v2(constants.MODEL_NAME, "model_v2.bin")
 
-@st.cache_resource
+# @st.cache_resource
 def plot(label, prob):
 
     ORANGE_COLOR = "#FF8000"
@@ -164,6 +193,11 @@ st.markdown("[![Duplicate Space](https://img.shields.io/badge/-Duplicate%20Space
 
 render_svg(open("assets/glotlid_logo.svg").read())
 
+render_metadata()
+
+st.markdown("**GlotLID** is an open-source language identification model with support for more than **1600 languages**.")
+
+
 tab1, tab2 = st.tabs(["Input a Sentence", "Upload a File"])
 
 with tab1:
@@ -192,18 +226,26 @@ with tab1:
     clicked = st.button("Submit")
 
     if sent:
-        sent = sent.replace('\n', '')
+        sent = sent.replace('\n', ' ')
         
         probs, labels = compute([sent], version=version)
         prob = probs[0]
         label = labels[0]
 
+        
+        # Check if the file exists
+        if not os.path.exists('logs.txt'):
+            with open('logs.txt', 'w') as file:
+                pass
+
+        print(f"{sent}, {label}: {prob}")
+        with open("logs.txt", "a") as f:
+            f.write(f"{sent}, {label}: {prob}\n")
+        
         # plot
         plot(label, prob)
         
-        print(sent)
-        with open("logs.txt", "a") as f:
-            f.write(sent + "\n")
+
 with tab2:
 
     version = st.radio(
@@ -255,3 +297,7 @@ with tab2:
                 file_name="GlotLID.csv",
                 mime="text/csv",
             )
+
+
+
+# citation()