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", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| FROM python:3.10-slim | |
| # Instalar dependencias del sistema | |
| RUN apt-get update && apt-get install -y \ | |
| ffmpeg \ | |
| git \ | |
| git-lfs \ | |
| build-essential \ | |
| python3-dev \ | |
| && rm -rf /var/lib/apt/lists/* | |
| # Configurar directorio de trabajo | |
| WORKDIR /app | |
| # Copiar archivos de requisitos | |
| COPY requirements.txt . | |
| # Instalar dependencias de Python | |
| RUN pip install --no-cache-dir -r requirements.txt | |
| # Descargar modelos de spaCy | |
| RUN python -m spacy download en_core_web_sm | |
| RUN python -m spacy download es_core_news_sm | |
| # Descargar datos de NLTK | |
| RUN python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('vader_lexicon')" | |
| # Copiar c贸digo de la aplicaci贸n | |
| COPY . . | |
| # Crear directorios necesarios | |
| RUN mkdir -p /app/.zenvision/cache /app/.zenvision/models /tmp/zenvision | |
| # Exponer puerto | |
| EXPOSE 7860 | |
| # Variables de entorno | |
| ENV GRADIO_SERVER_NAME="0.0.0.0" | |
| ENV GRADIO_SERVER_PORT=7860 | |
| # Comando de inicio | |
| CMD ["python", "app.py"] |