Initial implementation: Chatterbox TTS with ROCm and Wyoming

Wyoming-only server built around the official chatterbox TTS model.
Includes ROCm/AMD GPU support, sentence-level streaming, config.yaml
management, and Gitea CI for container builds.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Dockerfile.rocm

@@ -0,0 +1,43 @@
+FROM rocm/dev-ubuntu-22.04:latest
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    HF_HOME=/app/hf_cache \
+    PIP_NO_CACHE_DIR=1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3 \
+    python3-pip \
+    python3-dev \
+    git \
+    ffmpeg \
+    libsndfile1 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Step 1: Install ROCm-compatible PyTorch stack first.
+# This must happen before anything else to prevent pip from pulling CPU wheels.
+COPY requirements-rocm-init.txt .
+RUN pip3 install -r requirements-rocm-init.txt
+
+# Step 2: Install remaining dependencies (pinned to avoid overwriting torch).
+COPY requirements-rocm.txt .
+RUN pip3 install -r requirements-rocm.txt
+
+# Step 3: Install chatterbox with --no-deps so pip cannot replace ROCm torch.
+RUN pip3 install --no-deps chatterbox-tts
+
+# Application source
+COPY engine.py config.py wyoming_handler.py wyoming_voices.py main.py ./
+
+# Default config (can be overridden by volume mount)
+COPY config.yaml .
+
+# Create default directories
+RUN mkdir -p voices reference_audio hf_cache
+
+EXPOSE 10200
+
+CMD ["python3", "main.py"]