Update Dockerfile

Dockerfile

@@ -4,65 +4,60 @@ FROM python:3.10-slim
 # Set working directory
 WORKDIR /app
 
+# Set environment variables
+ENV PYTHONPATH="${PYTHONPATH}:/app"
+ENV HF_HOME="/tmp/huggingface"
+ENV PYTHONUNBUFFERED=1
+
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
     git \
     wget \
     curl \
     build-essential \
+    ffmpeg \
+    libsndfile1 \
     && rm -rf /var/lib/apt/lists/*
 
-# Install gdown for Google Drive downloads
-RUN pip install gdown
-
-# Copy requirements first to leverage Docker layer caching
-COPY requirements.txt .
-
 # Upgrade pip to latest version
 RUN pip install --upgrade pip
 
-# Install system dependencies for audio processing
-RUN apt-get update && apt-get install -y \
-    git \
-    wget \
-    curl \
-    build-essential \
-    ffmpeg \
-    libsndfile1 \
-    && rm -rf /var/lib/apt/lists/*
-
 # Install gdown for Google Drive downloads
 RUN pip install gdown
 
-# Copy requirements first to leverage Docker layer caching
-COPY requirements.txt .
-
 # Install core dependencies first
 RUN pip install --no-cache-dir torch torchaudio --index-url https://download.pytorch.org/whl/cpu
 
-# Install other dependencies
+# Copy requirements and install Python dependencies
+COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
 # Clone and install yarngpt
 RUN git clone https://github.com/saheedniyi02/yarngpt.git
 RUN cd yarngpt && pip install -e .
 
-# Download model files
-RUN wget https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml
-RUN gdown 1-ASeEkrn4HY49yZWHTASgfGFNXdVnLTt
+# Download model files with better error handling
+RUN echo "Downloading config file..." && \
+    wget -v -O wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml \
+    https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml
+
+RUN echo "Downloading model checkpoint..." && \
+    gdown --id 1-ASeEkrn4HY49yZWHTASgfGFNXdVnLTt -O wavtokenizer_large_speech_320_24k.ckpt
+
+# Verify files were downloaded
+RUN ls -la *.yaml *.ckpt
 
 # Copy application code
 COPY . .
 
+# Make startup script executable
+RUN chmod +x start.sh
+
 # Create audio files directory
 RUN mkdir -p audio_files
 
-# Expose port
+# Expose port 7860 (required by Hugging Face Spaces)
 EXPOSE 7860
 
-# Set environment variables
-ENV PYTHONPATH="${PYTHONPATH}:/app"
-ENV HF_HOME="/tmp/huggingface"
-
-# Run the application
-CMD ["python", "app.py"]
+# Run the application with startup script
+CMD ["./start.sh"]