[fix] Add support for loading model from a local path

[qibaoyuan]

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

Add support for loading token2wav_weights from a local absolute file path.

Test Plan

python3 end2end.py --model /to/path/llm/Qwen2.5-Omni-3B --prompts "who are you?" --voice-type "m02" --dit-ckpt none --bigvgan-ckpt none --output-wav output_audio --prompt_type text

Test Result

If not fixed, the result will be a model loading error:

(EngineCore_DP0 pid=7550)                 ^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=7550)   File "/Users/bob/.envs/vllm-omni-official/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
(EngineCore_DP0 pid=7550)     validate_repo_id(arg_value)
(EngineCore_DP0 pid=7550)   File "/Users/bob/.envs/vllm-omni-official/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
(EngineCore_DP0 pid=7550)     raise HFValidationError(
(EngineCore_DP0 pid=7550) huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/to/path//Qwen2.5-Omni-3B'. Use `repo_type` argument if needed.

After applying this patch, it works well.

(EngineCore_DP0 pid=9068) WARNING 11-09 04:21:12 [utils.py:72] Trying to guess the arguments for old-style model class <class 'vllm_omni.model_executor.models.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavModel'>
Loading safetensors checkpoint shards:   0% Completed | 0/3 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:00<00:00, 35.76it/s]
(EngineCore_DP0 pid=9068) 

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/hsliuustc0106/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

[Isotr0py]

LGTM, thanks!