Refactor code structure for improved readability and maintainability

workers/voice-to-text/Dockerfile

@@ -0,0 +1,20 @@
+# RunPod Serverless worker: Speech-to-Text (faster-whisper).
+# Lightweight — no torch/NeMo; ctranslate2 uses the CUDA + cuDNN in the base image.
+# Paths are relative to the REPO ROOT (RunPod's build context).
+FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        python3 python3-pip ffmpeg && \
+    ln -sf /usr/bin/python3 /usr/bin/python && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY workers/voice-to-text/requirements.txt .
+RUN pip3 install --no-cache-dir -r requirements.txt
+COPY workers/voice-to-text/handler.py .
+
+CMD ["python3", "-u", "handler.py"]