Upload app.py

app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+import sacrebleu
+from bert_score import score as bert_score
+
+# Function to calculate BLEU score
+def calculate_bleu(translations, references):
+    bleu = sacrebleu.corpus_bleu(translations, [references])
+    return bleu.score
+
+# Function to calculate TER score
+def calculate_ter(translations, references):
+    ter = sacrebleu.corpus_ter(translations, [references])
+    ter_score = ter.score
+    return ter_score
+
+# Function to calculate CHRF score
+def calculate_chrf(translations, references):
+    chrf = sacrebleu.corpus_chrf(translations, [references])
+    return chrf.score
+
+# Function to calculate BERTScore
+def calculate_bertscore(translations, references):
+    P, R, F1 = bert_score(translations, references, lang="en")
+    return F1.mean().item()
+
+# Streamlit app
+st.title("Machine Translation Quality Evaluation")
+st.write("Input the translated text and the reference translation to compute BLEU, TER, CHRF, and BERTScore metrics.")
+
+# Input fields for translations and references
+translation_input = st.text_area("Translated Text", height=200)
+reference_input = st.text_area("Reference Translation", height=200)
+
+# Evaluate button
+if st.button("Evaluate"):
+    translations = [translation_input]
+    references = [reference_input]
+
+    bleu_score = calculate_bleu(translations, references)
+    ter_score = calculate_ter(translations, references)
+    chrf_score = calculate_chrf(translations, references)
+    bertscore = calculate_bertscore(translations, references)
+
+    st.write(f"**BLEU Score:** {bleu_score:.2f}")
+    st.write(f"**TER Score:** {ter_score:.2f}")
+    st.write(f"**CHRF Score:** {chrf_score:.2f}")
+    st.write(f"**BERTScore:** {bertscore:.2f}")
+