Create app.py

app.py

@@ -0,0 +1,60 @@
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+import torch
+import json
+import gradio as gr
+
+text_translator = pipeline("translation", model="facebook/nllb-200-distilled-600M", torch_dtype=torch.bfloat16)
+
+# Load the JSON table
+with open('language.json') as f:
+    language_data = json.load(f)
+
+def get_flores_200_code(language):
+    for code in language_data:
+        if code['Language'] == language:
+            return code['FLORES-200 code']
+    return None
+
+def translate_text(text, destination_language):
+    
+    # text = "Hello friends how are you?"
+    dest_code = get_flores_200_code(destination_language)
+
+    translation = text_translator(text,
+                              src_lang="eng_Latn",
+                              tgt_lang=dest_code)
+    return translation[0]["translation_text"]
+
+gr.close_all()
+
+demo = gr.Interface(fn=translate_text,
+                    inputs=[gr.Textbox(label="Input text to translate",lines=6), gr.Dropdown(["English", "Bulgarian",
+"Croatian",
+"Czech",
+"Danish",
+"Dutch",
+"English",
+"Estonian",
+"Finnish",
+"French",
+"German",
+"Greek",
+"Hungarian",
+"Irish",
+"Italian",
+"Latvian",
+"Lithuanian",
+"Maltese",
+"Polish",
+"Portuguese",
+"Romanian",
+"Slovak",
+"Slovenian",
+"Spanish", 
+"Swedish"],label="Select destination language")],
+                    outputs=[gr.Textbox(label="Translated text", lines=4)],
+                    title="Multi Language translator - From European languages to English",
+                    description="This application uses NLLB model from Facebook trained on 200 languages for machine translation research",
+                    concurrency_limit=16)
+demo.launch()