[Frontend] Remove librosa from audio dependency (#37058)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

tests/multimodal/media/test_audio.py

@@ -10,6 +10,8 @@ import pytest
 
 from vllm.multimodal.media import AudioMediaIO
 
+from ...conftest import AudioTestAssets
+
 pytestmark = pytest.mark.cpu_test
 
 ASSETS_DIR = Path(__file__).parent.parent / "assets"
@@ -22,40 +24,32 @@ def dummy_audio():
 
 
 @pytest.fixture
-def dummy_audio_bytes():
-    return b"FAKEAUDIOBYTES"
+def dummy_audio_bytes(audio_assets: AudioTestAssets):
+    with open(audio_assets[0].get_local_path(), "rb") as f:
+        return f.read()
 
 
 def test_audio_media_io_load_bytes(dummy_audio_bytes):
     audio_io = AudioMediaIO()
-    with patch("librosa.load") as mock_load:
-        mock_load.return_value = (np.array([0.1, 0.2]), 16000)
-        out = audio_io.load_bytes(dummy_audio_bytes)
-        mock_load.assert_called_once()
-        assert isinstance(out[0], np.ndarray)
-        assert out[1] == 16000
+    out = audio_io.load_bytes(dummy_audio_bytes)
+    assert isinstance(out[0], np.ndarray)
+    assert out[1] == 16000
 
 
 def test_audio_media_io_load_base64(dummy_audio_bytes):
     audio_io = AudioMediaIO()
     encoded = base64.b64encode(dummy_audio_bytes).decode("utf-8")
-    with patch.object(AudioMediaIO, "load_bytes") as mock_load_bytes:
-        mock_load_bytes.return_value = (np.array([0.1, 0.2]), 16000)
-        out = audio_io.load_base64("audio/wav", encoded)
-        mock_load_bytes.assert_called_once()
-        assert isinstance(out[0], np.ndarray)
-        assert out[1] == 16000
+    out = audio_io.load_base64("audio/wav", encoded)
+    assert isinstance(out[0], np.ndarray)
+    assert out[1] == 16000
 
 
-def test_audio_media_io_load_file():
+def test_audio_media_io_load_file(audio_assets: AudioTestAssets):
     audio_io = AudioMediaIO()
-    path = Path("/fake/path.wav")
-    with patch("librosa.load") as mock_load:
-        mock_load.return_value = (np.array([0.1, 0.2]), 16000)
-        out = audio_io.load_file(path)
-        mock_load.assert_called_once_with(path, sr=None)
-        assert isinstance(out[0], np.ndarray)
-        assert out[1] == 16000
+    path = audio_assets[0].get_local_path()
+    out = audio_io.load_file(path)
+    assert isinstance(out[0], np.ndarray)
+    assert out[1] == 16000
 
 
 def test_audio_media_io_encode_base64(dummy_audio):