Add dual model support: M2M100 and NLLB-200

- Added optional 'model' parameter to translation request (default: m2m100)
- M2M100: 105 languages, Apache 2.0 License (commercial OK)
- NLLB-200: 200 languages, CC-BY-NC 4.0 License (non-commercial only)
- Updated /api/translate endpoint to accept model selection
- Updated /api/supported-languages to show languages per model
- Added comprehensive language name mappings for all NLLB-200 languages
- Both models can be used independently with automatic model loading
- Model information includes license and commercial use status

Example usage:
- Default (M2M100): {"text": "Hello", "source_lang": "en", "target_lang": "ko"}
- NLLB-200: {"text": "Hello", "source_lang": "en", "target_lang": "ko", "model": "nllb200"}

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

app/main.py

@@ -103,7 +103,8 @@ async def translate_text(request: TranslationRequest):
         translated_text, model_used = translator.translate(
             text=request.text,
             source_lang=request.source_lang,
-            target_lang=request.target_lang
+            target_lang=request.target_lang,
+            model_type=request.model
         )
 
         return TranslationResponse(
@@ -125,8 +126,15 @@ async def translate_text(request: TranslationRequest):
 
 
 @app.get("/api/supported-languages")
-async def get_supported_languages():
-    """Get list of supported languages"""
+async def get_supported_languages(model: str = "m2m100"):
+    """
+    Get list of supported languages for specified model
+
+    - **model**: Model type ('m2m100' or 'nllb200')
+    """
+
+    if model not in ["m2m100", "nllb200"]:
+        raise HTTPException(status_code=400, detail="Invalid model. Choose 'm2m100' or 'nllb200'")
 
     # Language names mapping
     lang_names = {
@@ -235,10 +243,97 @@ async def get_supported_languages():
         "tk": {"name": "Turkmen", "native": "Türkmençe"},
         "ug": {"name": "Uyghur", "native": "ئۇيغۇرچە"},
         "yi": {"name": "Yiddish", "native": "ייִדיש"},
+
+        # Additional NLLB-200 exclusive languages
+        "ace": {"name": "Acehnese", "native": "Acèh"},
+        "acm": {"name": "Mesopotamian Arabic", "native": "عراقي"},
+        "acq": {"name": "Ta'izzi-Adeni Arabic", "native": "تعزية-عدنية"},
+        "aeb": {"name": "Tunisian Arabic", "native": "تونسي"},
+        "ajp": {"name": "South Levantine Arabic", "native": "شامي"},
+        "als": {"name": "Tosk Albanian", "native": "Toskë"},
+        "ars": {"name": "Najdi Arabic", "native": "نجدي"},
+        "ary": {"name": "Moroccan Arabic", "native": "الدارجة"},
+        "arz": {"name": "Egyptian Arabic", "native": "مصري"},
+        "asm": {"name": "Assamese", "native": "অসমীয়া"},
+        "ast": {"name": "Asturian", "native": "Asturianu"},
+        "awa": {"name": "Awadhi", "native": "अवधी"},
+        "ayr": {"name": "Central Aymara", "native": "Aymar aru"},
+        "azb": {"name": "South Azerbaijani", "native": "تۆرکجه"},
+        "bak": {"name": "Bashkir", "native": "Башҡортса"},
+        "bam": {"name": "Bambara", "native": "Bamanankan"},
+        "ban": {"name": "Balinese", "native": "Basa Bali"},
+        "bho": {"name": "Bhojpuri", "native": "भोजपुरी"},
+        "bjn": {"name": "Banjar", "native": "Bahasa Banjar"},
+        "bod": {"name": "Tibetan", "native": "བོད་སྐད་"},
+        "bug": {"name": "Buginese", "native": "Basa Ugi"},
+        "crh": {"name": "Crimean Tatar", "native": "Qırımtatar tili"},
+        "cjk": {"name": "Chokwe", "native": "Chokwe"},
+        "ckb": {"name": "Central Kurdish", "native": "کوردیی ناوەندی"},
+        "dik": {"name": "Southwestern Dinka", "native": "Thuɔŋjäŋ"},
+        "dyu": {"name": "Dyula", "native": "Jula"},
+        "dzo": {"name": "Dzongkha", "native": "རྫོང་ཁ"},
+        "fur": {"name": "Friulian", "native": "Furlan"},
+        "fuv": {"name": "Nigerian Fulfulde", "native": "Fulfulde"},
+        "gaz": {"name": "West Central Oromo", "native": "Oromoo"},
+        "grn": {"name": "Guarani", "native": "Avañe'ẽ"},
+        "hne": {"name": "Chhattisgarhi", "native": "छत्तीसगढ़ी"},
+        "ilo": {"name": "Iloko", "native": "Ilokano"},
+        "kab": {"name": "Kabyle", "native": "Taqbaylit"},
+        "kac": {"name": "Jingpho", "native": "Jinghpaw"},
+        "kam": {"name": "Kamba", "native": "Kikamba"},
+        "kas": {"name": "Kashmiri", "native": "कॉशुर"},
+        "kea": {"name": "Kabuverdianu", "native": "Kabuverdianu"},
+        "khk": {"name": "Halh Mongolian", "native": "Монгол хэл"},
+        "kin": {"name": "Kinyarwanda", "native": "Ikinyarwanda"},
+        "lij": {"name": "Ligurian", "native": "Ligure"},
+        "lim": {"name": "Limburgish", "native": "Limburgs"},
+        "lin": {"name": "Lingala", "native": "Lingála"},
+        "lmo": {"name": "Lombard", "native": "Lombard"},
+        "ltg": {"name": "Latgalian", "native": "Latgalīšu"},
+        "luo": {"name": "Luo", "native": "Dholuo"},
+        "lus": {"name": "Mizo", "native": "Mizo ṭawng"},
+        "mag": {"name": "Magahi", "native": "मगही"},
+        "mai": {"name": "Maithili", "native": "मैथिली"},
+        "min": {"name": "Minangkabau", "native": "Baso Minangkabau"},
+        "mni": {"name": "Meitei", "native": "মৈতৈলোন্"},
+        "mos": {"name": "Mossi", "native": "Mooré"},
+        "mri": {"name": "Maori", "native": "Te Reo Māori"},
+        "nus": {"name": "Nuer", "native": "Thok Naath"},
+        "ory": {"name": "Odia", "native": "ଓଡ଼ିଆ"},
+        "pag": {"name": "Pangasinan", "native": "Pangasinan"},
+        "pap": {"name": "Papiamento", "native": "Papiamentu"},
+        "prs": {"name": "Dari", "native": "دری"},
+        "quy": {"name": "Ayacucho Quechua", "native": "Chanka Qhichwa"},
+        "run": {"name": "Rundi", "native": "Ikirundi"},
+        "sag": {"name": "Sango", "native": "Sängö"},
+        "san": {"name": "Sanskrit", "native": "संस्कृतम्"},
+        "sat": {"name": "Santali", "native": "ᱥᱟᱱᱛᱟᱲᱤ"},
+        "scn": {"name": "Sicilian", "native": "Sicilianu"},
+        "shn": {"name": "Shan", "native": "လိၵ်ႈတႆး"},
+        "srd": {"name": "Sardinian", "native": "Sardu"},
+        "szl": {"name": "Silesian", "native": "Ślōnski"},
+        "taq": {"name": "Tamasheq", "native": "Tamasheq"},
+        "tat": {"name": "Tatar", "native": "Татарча"},
+        "tir": {"name": "Tigrinya", "native": "ትግርኛ"},
+        "tpi": {"name": "Tok Pisin", "native": "Tok Pisin"},
+        "tsn": {"name": "Tswana", "native": "Setswana"},
+        "tso": {"name": "Tsonga", "native": "Xitsonga"},
+        "tum": {"name": "Tumbuka", "native": "Chitumbuka"},
+        "twi": {"name": "Twi", "native": "Twi"},
+        "tzm": {"name": "Central Atlas Tamazight", "native": "ⵜⴰⵎⴰⵣⵉⵖⵜ"},
+        "uig": {"name": "Uyghur", "native": "ئۇيغۇرچە"},
+        "vec": {"name": "Venetian", "native": "Vèneto"},
+        "war": {"name": "Waray", "native": "Winaray"},
+        "wol": {"name": "Wolof", "native": "Wolof"},
+        "xho": {"name": "Xhosa", "native": "isiXhosa"},
+        "ydd": {"name": "Eastern Yiddish", "native": "ייִדיש"},
+        "yor": {"name": "Yoruba", "native": "Yorùbá"},
+        "yue": {"name": "Cantonese", "native": "粵語"},
+        "zho_hant": {"name": "Chinese (Traditional)", "native": "繁體中文"},
     }
 
-    # Get all supported language codes from translator
-    supported_codes = list(translator.lang_codes.keys())
+    # Get all supported language codes from translator based on model type
+    supported_codes = list(translator.get_supported_languages(model).keys())
 
     # Build language list
     languages = [
@@ -250,7 +345,25 @@ async def get_supported_languages():
         for code in sorted(supported_codes)
     ]
 
+    model_info = {
+        "m2m100": {
+            "name": "M2M100",
+            "languages": 105,
+            "license": "Apache 2.0",
+            "commercial_use": True,
+            "model_id": "facebook/m2m100_418M"
+        },
+        "nllb200": {
+            "name": "NLLB-200",
+            "languages": 200,
+            "license": "CC-BY-NC 4.0",
+            "commercial_use": False,
+            "model_id": "facebook/nllb-200-distilled-600M"
+        }
+    }
+
     return {
+        "model": model_info[model],
         "languages": languages,
         "total_languages": len(languages),
         "note": "All language pairs are supported (any-to-any translation)"