Add Docker deployment support

README.md

@@ -63,6 +63,56 @@ pip install -r requirements.txt
 python server.py
 ```
 
+## Docker
+
+The repository now includes a container setup for running the API in Docker.
+
+### What gets mounted
+
+- `./config.docker.json` -> `/app/config.docker.json`
+- `./logs` -> `/app/logs`
+- `./history` -> `/app/history`
+- `./models` -> `/models`
+
+Place your Whisper model inside `./models/whisper` or update `model_path` in `config.docker.json`.
+
+### Build and run with Docker Compose
+
+```bash
+docker compose up --build
+```
+
+The API will be available at:
+
+```text
+http://localhost:5042
+```
+
+### Build and run with plain Docker
+
+```bash
+docker build -t whisper-api-server .
+docker run --rm -p 5042:5042 \
+  -v "$(pwd)/config.docker.json:/app/config.docker.json:ro" \
+  -v "$(pwd)/logs:/app/logs" \
+  -v "$(pwd)/history:/app/history" \
+  -v "$(pwd)/models:/models" \
+  whisper-api-server
+```
+
+### GPU note
+
+The container image installs the same Python dependencies as the local setup, including CUDA-oriented PyTorch wheels on Linux x86_64. To actually use NVIDIA GPU acceleration at runtime, start the container with GPU access enabled in your Docker environment, for example:
+
+```bash
+docker run --rm --gpus all -p 5042:5042 \
+  -v "$(pwd)/config.docker.json:/app/config.docker.json:ro" \
+  -v "$(pwd)/logs:/app/logs" \
+  -v "$(pwd)/history:/app/history" \
+  -v "$(pwd)/models:/models" \
+  whisper-api-server
+```
+
 ## Configuration
 
 The service is configured through the `config.json` file: