[llm_bench] Add support smolvlm for optimum only (openvinotoolkit#2957)

## Description
<!-- Please include a summary of the change. Also include relevant
motivation and context. -->
add support of smolvlm to llm_bench, it's not working for GenAI, but
working with optimum-intel

<!--- Jira ticket number (e.g., 123). Delete if there's no ticket. Don't
include full link or project name. -->
Ticket: CVS-174310


## Checklist:
- [ ] Tests have been updated or added to cover the new code <!--- If
the change isn't maintenance related, update the tests at
https://github.com/openvinotoolkit/openvino.genai/tree/master/tests or
explain in the description why the tests don't need an update. -->
- [ ] This patch fully addresses the ticket. <!--- If follow-up pull
requests are needed, specify in description. -->
- [ ] I have made corresponding changes to the documentation

Author: sbalandi

tools/llm_bench/llm_bench_utils/config_class.py

@@ -128,7 +128,7 @@ class UseCaseTextToSpeech(UseCase):
 USE_CASES = {
     'image_gen': [UseCaseImageGen(['stable-diffusion-', 'ssd-', 'tiny-sd', 'small-sd', 'lcm-', 'sdxl', 'dreamlike', "flux"])],
     "visual_text_gen": [UseCaseVLM(["llava", "llava-next", "qwen2-vl", "llava-qwen2", "internvl-chat", "minicpmv", "phi3-v",
-                                    "minicpm-v", "minicpmo", "maira2", "qwen2-5-vl"])],
+                                    "minicpm-v", "minicpmo", "maira2", "qwen2-5-vl", "smolvlm"])],
     'speech_to_text': [UseCaseSpeech2Text(['whisper'])],
     'image_cls': [UseCaseImageCls(['vit'])],
     'code_gen': [UseCaseCodeGen(["codegen", "codegen2", "stable-code"]),

tools/llm_bench/requirements.txt

@@ -20,3 +20,4 @@ jinja2>=3.1.0
 scipy
 gguf_parser
 gguf>=0.10
+num2words