Changing whisper device to GPU (#4154)

### 🛠 Summary

Changing whisper device to GPU 

### 🧪 Checklist

- [ ] Unit tests added.
- [ ] The documentation updated.
- [ ] Change follows security best practices.
``

Author: przepeck

demos/integration_with_OpenWebUI/README.md

@@ -25,7 +25,7 @@ There are other options to fulfill the prerequisites like [OpenVINO Model Server
 
 This demo can be followed without changes on Panther Lake host with 64GB RAM and VRAM allocation to GPU extended using Intel Graphics Software. That way all the mentioned models can be loaded simultaneously. It's also possible to use [llama-swap](https://github.com/openvinotoolkit/model_server/blob/main/extras/llama_swap/README.md) integration to reload the models automatically. On hosts with less VRAM available, use a subset of the models, apply other models or configure different target device like CPU or NPU. Check this list of [preconfigured OpenVINO models](https://huggingface.co/OpenVINO).
 
-## Step 1: Pull model and start the OVMS sever
+## Step 1: Pull model and start the OVMS server
 ::::{tab-set}
 :::{tab-item} Windows
 :sync: Windows
@@ -363,7 +363,7 @@ mcpo --port 9000 -- python -m mcp_weather_server
 
 ## Using Web Search
 
-### Step 1: Configure WebSearch
+### Step 1: Configure Web Search
 
 1. Go to **Admin Panel** → **Settings** → **Web Search**
 2. Enable **Web Search**
@@ -474,14 +474,14 @@ Next, download and add to config model for transcription:
 :::{tab-item} Windows
 :sync: Windows
 ```bat
-ovms.exe --pull --source_model OpenVINO/whisper-base-fp16-ov --model_repository_path models --task speech2text
+ovms.exe --pull --source_model OpenVINO/whisper-base-fp16-ov --model_repository_path models --task speech2text --target_device GPU
 ovms.exe --add_to_config --config_path  models\config.json --model_path OpenVINO\whisper-base-fp16-ov --model_name OpenVINO/whisper-base-fp16-ov
 ```
 :::
 :::{tab-item} Linux (using Docker)
 :sync: Linux
 ```bash
-docker run --rm -u $(id -u):$(id -g) -v $PWD/models:/models openvino/model_server:weekly --pull --source_model OpenVINO/whisper-base-fp16-ov --model_repository_path /models --task speech2text
+docker run --rm -u $(id -u):$(id -g) --device /dev/dri --group-add=$(stat -c "%g" /dev/dri/render* | head -n 1) -v $PWD/models:/models openvino/model_server:weekly --pull --source_model OpenVINO/whisper-base-fp16-ov --model_repository_path /models --task speech2text --target_device GPU
 docker run --rm -u $(id -u):$(id -g) -v $PWD/models:/models openvino/model_server:weekly --add_to_config --config_path /models/config.json --model_path OpenVINO/whisper-base-fp16-ov --model_name OpenVINO/whisper-base-fp16-ov
 ```
 :::