Dockerfile

# Use a Hugging Face image with PyTorch and Transformers
FROM huggingface/transformers-pytorch-gpu:latest

# Set the working directory inside the container
WORKDIR /app

# Copy the requirements file first (to leverage Docker's caching mechanism)
COPY requirements.txt .

# Ensure the results directory has the right permissions
RUN mkdir -p /app/results && chmod -R 777 /app/results
RUN mkdir -p /app/saved_model && chmod -R 777 /app/saved_model

# Set the environment variable for Hugging Face cache
RUN mkdir -p /tmp/transformers_cache && chmod -R 777 /tmp/transformers_cache
ENV TRANSFORMERS_CACHE=/tmp/transformers_cache
ENV HF_HOME=/tmp/transformers_cache

# Install and update python3
RUN apt update
RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
RUN python3 -m pip install --no-cache-dir --upgrade pip

# Install dependencies
RUN python3 -m pip install --no-cache-dir -r requirements.txt

# Copy all remaining files into the container
COPY . .

# Run the training script when the container starts
CMD ["python3", "train.py"]