Automatic Speech Recognition
Transformers
PyTorch
zenvision
ai
subtitles
video
transcription
translation
nlp
whisper
bert
computer-vision
audio-processing
multimodal
Eval Results (legacy)
Instructions to use Darveht/ZenVision-AI-Subtitle-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Darveht/ZenVision-AI-Subtitle-Generator with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Darveht/ZenVision-AI-Subtitle-Generator")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Darveht/ZenVision-AI-Subtitle-Generator", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| # ZenVision AI Subtitle Generator - Installation Script | |
| # Instala todas las dependencias y modelos necesarios | |
| set -e | |
| echo "🚀 Instalando ZenVision AI Subtitle Generator..." | |
| echo "==================================================" | |
| # Colors for output | |
| RED='\033[0;31m' | |
| GREEN='\033[0;32m' | |
| YELLOW='\033[1;33m' | |
| BLUE='\033[0;34m' | |
| NC='\033[0m' # No Color | |
| # Function to print colored output | |
| print_status() { | |
| echo -e "${BLUE}[INFO]${NC} $1" | |
| } | |
| print_success() { | |
| echo -e "${GREEN}[SUCCESS]${NC} $1" | |
| } | |
| print_warning() { | |
| echo -e "${YELLOW}[WARNING]${NC} $1" | |
| } | |
| print_error() { | |
| echo -e "${RED}[ERROR]${NC} $1" | |
| } | |
| # Check Python version | |
| print_status "Verificando versión de Python..." | |
| python_version=$(python3 --version 2>&1 | awk '{print $2}' | cut -d. -f1,2) | |
| required_version="3.8" | |
| if [ "$(printf '%s\n' "$required_version" "$python_version" | sort -V | head -n1)" = "$required_version" ]; then | |
| print_success "Python $python_version encontrado" | |
| else | |
| print_error "Python $required_version o superior requerido. Encontrado: $python_version" | |
| exit 1 | |
| fi | |
| # Check if running on supported OS | |
| print_status "Detectando sistema operativo..." | |
| if [[ "$OSTYPE" == "linux-gnu"* ]]; then | |
| OS="linux" | |
| print_success "Sistema Linux detectado" | |
| elif [[ "$OSTYPE" == "darwin"* ]]; then | |
| OS="macos" | |
| print_success "Sistema macOS detectado" | |
| elif [[ "$OSTYPE" == "msys" ]] || [[ "$OSTYPE" == "cygwin" ]]; then | |
| OS="windows" | |
| print_success "Sistema Windows detectado" | |
| else | |
| print_warning "Sistema operativo no reconocido: $OSTYPE" | |
| OS="unknown" | |
| fi | |
| # Install system dependencies | |
| print_status "Instalando dependencias del sistema..." | |
| if [[ "$OS" == "linux" ]]; then | |
| if command -v apt-get &> /dev/null; then | |
| sudo apt-get update | |
| sudo apt-get install -y ffmpeg python3-dev python3-pip build-essential | |
| print_success "Dependencias de Ubuntu/Debian instaladas" | |
| elif command -v yum &> /dev/null; then | |
| sudo yum install -y ffmpeg python3-devel python3-pip gcc gcc-c++ | |
| print_success "Dependencias de CentOS/RHEL instaladas" | |
| elif command -v pacman &> /dev/null; then | |
| sudo pacman -S --noconfirm ffmpeg python python-pip base-devel | |
| print_success "Dependencias de Arch Linux instaladas" | |
| else | |
| print_warning "Gestor de paquetes no reconocido. Instala manualmente: ffmpeg, python3-dev" | |
| fi | |
| elif [[ "$OS" == "macos" ]]; then | |
| if command -v brew &> /dev/null; then | |
| brew install ffmpeg | |
| print_success "FFmpeg instalado via Homebrew" | |
| else | |
| print_warning "Homebrew no encontrado. Instala FFmpeg manualmente" | |
| fi | |
| fi | |
| # Create virtual environment | |
| print_status "Creando entorno virtual..." | |
| if [ ! -d "venv" ]; then | |
| python3 -m venv venv | |
| print_success "Entorno virtual creado" | |
| else | |
| print_warning "Entorno virtual ya existe" | |
| fi | |
| # Activate virtual environment | |
| print_status "Activando entorno virtual..." | |
| source venv/bin/activate | |
| print_success "Entorno virtual activado" | |
| # Upgrade pip | |
| print_status "Actualizando pip..." | |
| pip install --upgrade pip setuptools wheel | |
| # Install PyTorch with CUDA support if available | |
| print_status "Detectando soporte CUDA..." | |
| if command -v nvidia-smi &> /dev/null; then | |
| print_success "NVIDIA GPU detectada, instalando PyTorch con CUDA" | |
| pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu118 | |
| else | |
| print_warning "No se detectó GPU NVIDIA, instalando PyTorch CPU" | |
| pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu | |
| fi | |
| # Install Python dependencies | |
| print_status "Instalando dependencias de Python..." | |
| pip install -r requirements.txt | |
| print_success "Dependencias de Python instaladas" | |
| # Download spaCy models | |
| print_status "Descargando modelos de spaCy..." | |
| python -m spacy download en_core_web_sm | |
| python -m spacy download es_core_news_sm | |
| # Try to download additional language models | |
| for lang in fr de it pt; do | |
| print_status "Intentando descargar modelo de spaCy para $lang..." | |
| python -m spacy download ${lang}_core_news_sm || print_warning "Modelo $lang no disponible" | |
| done | |
| print_success "Modelos de spaCy descargados" | |
| # Download NLTK data | |
| print_status "Descargando datos de NLTK..." | |
| python -c " | |
| import nltk | |
| nltk.download('punkt') | |
| nltk.download('stopwords') | |
| nltk.download('vader_lexicon') | |
| print('Datos de NLTK descargados') | |
| " | |
| # Create necessary directories | |
| print_status "Creando directorios necesarios..." | |
| mkdir -p ~/.zenvision/cache | |
| mkdir -p ~/.zenvision/models | |
| mkdir -p /tmp/zenvision | |
| print_success "Directorios creados" | |
| # Test installation | |
| print_status "Probando instalación..." | |
| python -c " | |
| import torch | |
| import whisper | |
| import transformers | |
| import gradio | |
| import moviepy | |
| import librosa | |
| import cv2 | |
| import spacy | |
| print('✅ Todas las librerías principales importadas correctamente') | |
| # Test CUDA availability | |
| if torch.cuda.is_available(): | |
| print(f'✅ CUDA disponible: {torch.cuda.get_device_name(0)}') | |
| else: | |
| print('⚠️ CUDA no disponible, usando CPU') | |
| # Test Whisper | |
| try: | |
| model = whisper.load_model('tiny') | |
| print('✅ Whisper cargado correctamente') | |
| except Exception as e: | |
| print(f'❌ Error cargando Whisper: {e}') | |
| " | |
| # Create launcher script | |
| print_status "Creando script de lanzamiento..." | |
| cat > run_zenvision.sh << 'EOF' | |
| #!/bin/bash | |
| cd "$(dirname "$0")" | |
| source venv/bin/activate | |
| python app.py | |
| EOF | |
| chmod +x run_zenvision.sh | |
| print_success "Script de lanzamiento creado: ./run_zenvision.sh" | |
| # Display system information | |
| print_status "Información del sistema:" | |
| echo " - Python: $(python --version)" | |
| echo " - PyTorch: $(python -c 'import torch; print(torch.__version__)')" | |
| echo " - CUDA disponible: $(python -c 'import torch; print(torch.cuda.is_available())')" | |
| echo " - Dispositivos CUDA: $(python -c 'import torch; print(torch.cuda.device_count())')" | |
| # Calculate approximate model size | |
| print_status "Calculando tamaño aproximado de modelos..." | |
| echo " - Whisper large-v2: ~1.5 GB" | |
| echo " - BERT multilingual: ~400 MB" | |
| echo " - RoBERTa sentiment: ~200 MB" | |
| echo " - DistilRoBERTa emotion: ~300 MB" | |
| echo " - Modelos de traducción: ~500 MB" | |
| echo " - Otros modelos: ~300 MB" | |
| echo " - TOTAL APROXIMADO: ~3.2 GB" | |
| print_success "¡Instalación completada!" | |
| echo "" | |
| echo "==================================================" | |
| echo "🎬 ZenVision AI Subtitle Generator está listo!" | |
| echo "==================================================" | |
| echo "" | |
| echo "Para ejecutar la aplicación:" | |
| echo " 1. Activar entorno virtual: source venv/bin/activate" | |
| echo " 2. Ejecutar aplicación: python app.py" | |
| echo " 3. O usar el script: ./run_zenvision.sh" | |
| echo "" | |
| echo "La aplicación estará disponible en: http://localhost:7860" | |
| echo "" | |
| echo "Para más información, consulta el README.md" | |
| echo "" | |
| print_success "¡Disfruta usando ZenVision! 🚀" |