voice clone config and improved installation/launch

Dockerfile_gpu

@@ -1,45 +1,35 @@
-# Use NVIDIA CUDA base image (includes nvcc compiler for building)
-FROM nvidia/cuda:12.4.1-devel-ubuntu22.04
+# Use PyTorch image with CUDA support (includes Python 3.11, PyTorch, CUDA)
+FROM pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel
 
-# Avoid interactive prompts during package installation
+# Avoid interactive prompts
 ENV DEBIAN_FRONTEND=noninteractive
 
-# Install Python 3.12 and build tools
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
-    software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa \
-    && apt-get update && apt-get install -y \
-    python3.12 \
-    python3.12-venv \
-    python3.12-dev \
-    python3-pip \
     git \
-    build-essential \
-    cmake \
+    sox \
+    libsox-dev \
+    libsox-fmt-all \
+    ffmpeg \
     && rm -rf /var/lib/apt/lists/*
 
-# Set Python 3.12 as default
-RUN ln -s /usr/bin/python3.12 /usr/bin/python
-
 WORKDIR /app
 
-# 2. Set Environment Variables to force CUDA build
-# -DGGML_CUDA=on is the flag for recent llama-cpp-python versions (0.3.x)
+# Set Environment Variables for llama-cpp-python CUDA build
 ENV CMAKE_ARGS="-DGGML_CUDA=on"
 ENV FORCE_CMAKE=1
 
+# Install Python dependencies
 COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt && \
+    pip install --no-deps git+https://github.com/rekuenkdr/Qwen3-TTS-streaming.git@97da215 && \
+    pip install flash-attn --no-build-isolation
 
-# 3. Install dependencies
-# This will now compile llama-cpp-python with CUDA support
-RUN python3.12 -m pip install --upgrade pip && \
-    python3.12 -m pip install --no-cache-dir -r requirements.txt
-
-# Copy application files (ignoring __pycache__ via .dockerignore)
+# Copy application code
 COPY app.py .
+COPY core/ core/
 COPY tools/ tools/
 COPY utils/ utils/
-COPY wav/ wav/
 COPY audio/ audio/
 
-CMD ["python3.12", "app.py"]
+CMD ["python", "app.py"]