Create multilingual translator code

multiligual translator code

@@ -0,0 +1,64 @@
+import torch
+import torch.nn.functional as F
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModelForSeq2SeqLM
+from sentence_transformers import SentenceTransformer
+import gradio as gr
+
+# Load models
+lang_detect_model = AutoModelForSequenceClassification.from_pretrained("papluca/xlm-roberta-base-language-detection")
+lang_detect_tokenizer = AutoTokenizer.from_pretrained("papluca/xlm-roberta-base-language-detection")
+trans_model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M")
+trans_tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
+
+# Language maps
+id2lang = lang_detect_model.config.id2label
+
+nllb_langs = {
+    "eng_Latn": "English", "fra_Latn": "French", "hin_Deva": "Hindi",
+    "spa_Latn": "Spanish", "deu_Latn": "German", "tam_Taml": "Tamil",
+    "tel_Telu": "Telugu", "jpn_Jpan": "Japanese", "zho_Hans": "Chinese",
+    "arb_Arab": "Arabic", "san_Deva": "Sanskrit"
+}
+
+xlm_to_nllb = {
+    "en": "eng_Latn", "fr": "fra_Latn", "hi": "hin_Deva", "es": "spa_Latn", "de": "deu_Latn",
+    "ta": "tam_Taml", "te": "tel_Telu", "ja": "jpn_Jpan", "zh": "zho_Hans", "ar": "arb_Arab",
+    "sa": "san_Deva"
+}
+
+# Detection
+def detect_language(text):
+    inputs = lang_detect_tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = lang_detect_model(**inputs)
+        probs = F.softmax(outputs.logits, dim=1)
+        pred = torch.argmax(probs, dim=1).item()
+    return id2lang[pred]
+
+# Translation
+def translate_text(input_text, target_code):
+    detected = detect_language(input_text)
+    src_nllb = xlm_to_nllb.get(detected, "eng_Latn")
+    trans_tokenizer.src_lang = src_nllb
+    encoded = trans_tokenizer(input_text, return_tensors="pt", truncation=True, padding=True)
+    try:
+        lang_id = trans_tokenizer.convert_tokens_to_ids([target_code])[0]
+        generated = trans_model.generate(**encoded, forced_bos_token_id=lang_id)
+        result = trans_tokenizer.decode(generated[0], skip_special_tokens=True)
+        return f"Detected: {detected}\n\nTranslated:\n{result}"
+    except:
+        return "Translation failed."
+
+# Gradio UI
+demo = gr.Interface(
+    fn=translate_text,
+    inputs=[
+        gr.Textbox(label="Input Text", lines=6),
+        gr.Dropdown(choices=list(nllb_langs.keys()), label="Target Language")
+    ],
+    outputs="text",
+    title="Multilingual Text Translator 🌍",
+    description="Enter your text and select a target language to translate."
+)
+
+demo.launch()