Upload Dockerfile with huggingface_hub

Dockerfile

@@ -0,0 +1,64 @@
+FROM nvidia/cuda:11.8-devel-ubuntu22.04
+
+# Set environment variables
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+ENV TRANSFORMERS_CACHE=/app/model_cache
+ENV HF_HOME=/app/model_cache
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip \
+    python3-dev \
+    ffmpeg \
+    portaudio19-dev \
+    libasound2-dev \
+    libsndfile1 \
+    git \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create app directory and model cache directory
+WORKDIR /app
+RUN mkdir -p /app/model_cache
+
+# Copy requirements first for better Docker layer caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip3 install --no-cache-dir --upgrade pip
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+# Pre-download and cache the model during build
+RUN python3 -c "
+import os
+os.environ['TRANSFORMERS_CACHE'] = '/app/model_cache'
+os.environ['HF_HOME'] = '/app/model_cache'
+
+from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForConditionalGeneration
+print('Downloading and caching model...')
+
+model_id = 'kyutai/stt-1b-en_fr'
+processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id, cache_dir='/app/model_cache')
+model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, cache_dir='/app/model_cache')
+
+print('Model cached successfully at /app/model_cache')
+print('Processor cached successfully')
+"
+
+# Copy application files
+COPY app.py .
+
+# Set permissions for model cache
+RUN chmod -R 755 /app/model_cache
+
+# Expose port
+EXPOSE 7860
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:7860/health || exit 1
+
+# Run the application
+CMD ["python3", "app.py"]