config.py

#!/usr/bin/env python3
"""
Configuration file for Translation AI Agent
"""

import os
from typing import Dict, List

class Config:
    """Configuration settings for the AI Agent"""
    
    # Model Configuration
    TRANSLATION_MODEL = "facebook/nllb-200-distilled-600M"
    SPEECH_RECOGNITION_MODEL = "openai/whisper-base"
    TEXT_TO_SPEECH_MODEL = "microsoft/speecht5_tts"
    
    # Alternative models for different performance/quality tradeoffs
    MODEL_ALTERNATIVES = {
        "translation": {
            "small": "facebook/nllb-200-distilled-600M",
            "medium": "facebook/nllb-200-1.3B",
            "large": "facebook/nllb-200-3.3B"
        },
        "speech_recognition": {
            "tiny": "openai/whisper-tiny",
            "base": "openai/whisper-base", 
            "small": "openai/whisper-small",
            "medium": "openai/whisper-medium"
        },
        "tts": {
            "speecht5": "microsoft/speecht5_tts",
            "bark": "suno/bark"
        }
    }
    
    # Supported Languages
    SUPPORTED_LANGUAGES = {
        'en': 'English',
        'es': 'Spanish',
        'fr': 'French', 
        'de': 'German',
        'it': 'Italian',
        'pt': 'Portuguese',
        'ru': 'Russian',
        'ja': 'Japanese',
        'ko': 'Korean',
        'zh': 'Chinese',
        'ar': 'Arabic',
        'hi': 'Hindi',
        'vi': 'Vietnamese',
        'th': 'Thai',
        'tr': 'Turkish',
        'nl': 'Dutch',
        'pl': 'Polish',
        'sv': 'Swedish',
        'da': 'Danish',
        'no': 'Norwegian'
    }
    
    # Language Detection Keywords
    LANGUAGE_KEYWORDS = {
        'en': ['the', 'and', 'is', 'in', 'to', 'of', 'a', 'that', 'it', 'with'],
        'es': ['el', 'la', 'de', 'que', 'y', 'en', 'un', 'es', 'se', 'no'],
        'fr': ['le', 'de', 'et', 'à', 'un', 'il', 'être', 'et', 'en', 'avoir'],
        'de': ['der', 'die', 'und', 'in', 'den', 'von', 'zu', 'das', 'mit', 'sich'],
        'it': ['di', 'a', 'da', 'in', 'con', 'su', 'per', 'tra', 'fra', 'la'],
        'pt': ['de', 'a', 'o', 'que', 'e', 'do', 'da', 'em', 'um', 'para'],
        'ru': ['в', 'и', 'не', 'на', 'я', 'с', 'что', 'а', 'по', 'это'],
        'ja': ['の', 'に', 'は', 'を', 'た', 'が', 'で', 'て', 'と', 'し'],
        'ko': ['이', '가', '을', '를', '에', '의', '와', '과', '로', '으로'],
        'zh': ['的', '一', '是', '在', '不', '了', '有', '和', '人', '这'],
        'ar': ['في', 'من', 'إلى', 'على', 'أن', 'هذا', 'هذه', 'التي', 'التي', 'كان'],
        'hi': ['का', 'के', 'की', 'में', 'है', 'और', 'को', 'से', 'पर', 'या'],
        'vi': ['và', 'của', 'có', 'trong', 'một', 'là', 'với', 'này', 'để', 'được']
    }
    
    # Audio Configuration
    AUDIO_SAMPLE_RATE = 16000
    AUDIO_CHUNK_DURATION = 30  # seconds
    MAX_AUDIO_DURATION = 300   # seconds (5 minutes)
    SUPPORTED_AUDIO_FORMATS = ['.wav', '.mp3', '.m4a', '.flac', '.ogg']
    
    # Model Performance Settings
    MAX_LENGTH = 512
    BATCH_SIZE = 1
    DEVICE_MAP = "auto"
    TORCH_DTYPE = "float16"
    
    # Environment Variables
    HUGGINGFACE_TOKEN = os.getenv("HUGGING_FACE_HUB_TOKEN")
    CUDA_VISIBLE_DEVICES = os.getenv("CUDA_VISIBLE_DEVICES", "0")
    TRANSFORMERS_CACHE = os.getenv("TRANSFORMERS_CACHE", "./cache")
    
    # Gradio Configuration  
    GRADIO_CONFIG = {
        "server_name": "0.0.0.0",
        "server_port": int(os.getenv("PORT", "7860")),
        "share": os.getenv("GRADIO_SHARE", "True").lower() == "true",
        "debug": os.getenv("DEBUG", "False").lower() == "true",
        "show_error": True,
        "quiet": False,
        "inbrowser": False,
        "auth": None  # Can be set to ("username", "password") for authentication
    }
    
    # Theme Configuration
    GRADIO_THEME = "soft"  # Options: default, soft, monochrome, glass, etc.
    
    # Custom CSS
    CUSTOM_CSS = """
    .gradio-container {
        max-width: 1200px !important;
        margin: auto !important;
        font-family: 'Inter', sans-serif;
    }
    
    .header {
        text-align: center;
        padding: 25px;
        background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
        color: white;
        border-radius: 15px;
        margin-bottom: 20px;
        box-shadow: 0 8px 32px rgba(102, 126, 234, 0.3);
    }
    
    .tab-nav button {
        font-weight: 600;
        border-radius: 10px;
        margin: 5px;
        transition: all 0.3s ease;
    }
    
    .tab-nav button:hover {
        transform: translateY(-2px);
        box-shadow: 0 4px 12px rgba(0,0,0,0.15);
    }
    
    .gr-button {
        border-radius: 8px;
        font-weight: 600;
        transition: all 0.3s ease;
    }
    
    .gr-button:hover {
        transform: translateY(-1px);
        box-shadow: 0 4px 12px rgba(0,0,0,0.15);
    }
    
    .gr-textbox, .gr-dropdown {
        border-radius: 8px;
        border: 2px solid #e5e7eb;
        transition: all 0.3s ease;
    }
    
    .gr-textbox:focus, .gr-dropdown:focus {
        border-color: #667eea;
        box-shadow: 0 0 0 3px rgba(102, 126, 234, 0.1);
    }
    """
    
    # Logging Configuration
    LOGGING_CONFIG = {
        'version': 1,
        'disable_existing_loggers': False,
        'formatters': {
            'standard': {
                'format': '%(asctime)s [%(levelname)s] %(name)s: %(message)s'
            },
        },
        'handlers': {
            'default': {
                'level': 'INFO',
                'formatter': 'standard',
                'class': 'logging.StreamHandler',
            },
        },
        'loggers': {
            '': {
                'handlers': ['default'],
                'level': 'INFO',
                'propagate': False
            }
        }
    }
    
    # Rate Limiting (for production deployment)
    RATE_LIMIT = {
        "calls_per_minute": 60,
        "calls_per_hour": 1000
    }
    
    # Feature Flags
    FEATURES = {
        "enable_live_translation": True,
        "enable_batch_processing": True,
        "enable_custom_models": False,
        "enable_analytics": True,
        "enable_caching": True
    }
    
    # Cache Configuration
    CACHE_CONFIG = {
        "translation_cache_size": 1000,
        "model_cache_dir": "./cache/models",
        "audio_cache_dir": "./cache/audio",
        "cache_ttl": 3600  # 1 hour
    }

    @classmethod
    def get_model_config(cls, model_size: str = "base") -> Dict[str, str]:
        """Get model configuration based on size preference"""
        return {
            "translation": cls.MODEL_ALTERNATIVES["translation"].get(model_size, cls.TRANSLATION_MODEL),
            "speech_recognition": cls.MODEL_ALTERNATIVES["speech_recognition"].get(model_size, cls.SPEECH_RECOGNITION_MODEL),
            "tts": cls.MODEL_ALTERNATIVES["tts"]["speecht5"]
        }
    
    @classmethod 
    def get_language_pairs(cls) -> List[tuple]:
        """Get all possible language pairs for translation"""
        langs = list(cls.SUPPORTED_LANGUAGES.keys())
        pairs = []
        for src in langs:
            for tgt in langs:
                if src != tgt:
                    pairs.append((src, tgt))
        return pairs
    
    @classmethod
    def validate_language(cls, lang_code: str) -> bool:
        """Validate if language code is supported"""
        return lang_code in cls.SUPPORTED_LANGUAGES
    
    @classmethod
    def get_language_name(cls, lang_code: str) -> str:
        """Get language display name from code"""
        return cls.SUPPORTED_LANGUAGES.get(lang_code, lang_code)

# Create global config instance
config = Config()