[Test] Skip tests for known issues in audio and speaker recognition (#2851)

tests/e2e/online_serving/test_qwen3_omni_expansion.py

@@ -371,6 +371,7 @@ def test_mix_to_text_audio_001(omni_server, openai_client) -> None:
 @pytest.mark.omni
 @hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
+@pytest.mark.skip(reason="issue: #2827")
 def test_audio_in_video_001(omni_server, openai_client) -> None:
     """
     Input Modal: text + video (synthetic MP4 with embedded audio; ``use_audio_in_video`` uses audio from the video).
@@ -491,6 +492,7 @@ def test_speaker_001(omni_server, openai_client) -> None:
 @pytest.mark.omni
 @hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
+@pytest.mark.skip(reason="Known issue: occasional inaccuracy in voice recognition.")
 def test_speaker_002(omni_server, openai_client) -> None:
     """
     Input Modal: text only (one-word answer constraint).