changed folder position

test/test_audio.py

@@ -0,0 +1,123 @@
+import pytest
+from .audio import AudioProcessor
+import torch
+
+
+
+DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+TEST_WAVEFORM = torch.tensor([]).to(DEVICE)
+TEST_SR = 16000
+SAMPLE_RATE = 16000
+NORMALIZATION_FACTOR = 32768
+
+
+@pytest.fixture
+def probe_audio_processor():
+    """Fixture for creating an instance of the AudioProcessor class with test waveform and sample rate. 
+    
+    This fixture is used to create an instance of the AudioProcessor class with a predfined test waveform and sample rate (TEST_SR). It returns the instantiated AudioProcessor , which can bes used as a 
+    dependency in other test functions.
+
+
+    Returns:
+        AudioProcessor (obj): An instance of the AudioProcessor class with the test waveform and sample rate.
+    """    
+    return AudioProcessor(TEST_WAVEFORM, TEST_SR)
+
+
+
+
+
+
+def test_AudioProcessor_init(probe_audio_processor):
+    """
+    Test the initialization of the AudioProcessor class.
+
+    This test verifies that the AUdioProcessor class is correctly initialized with the provided waveform and sample rate. It checks whether the instantiated AhdioProcessor object has the correct attributes
+    and whether the waveform and sample rate match the expected values.
+
+    Args:
+        probe_audio_processor (obj): An instance of the AudioProcessor class to be tested.
+
+
+    Returns:
+           None
+
+    
+
+        
+    """    
+    assert isinstance(probe_audio_processor, AudioProcessor)
+    assert probe_audio_processor.waveform.device == TEST_WAVEFORM.device
+    assert torch.equal(probe_audio_processor.waveform, TEST_WAVEFORM)
+    assert probe_audio_processor.sr == TEST_SR
+
+
+
+def test_cut():
+    """Test the cut function of the AudioProcessor class.
+    
+    This test verifies that the cut function correctly extracts a segment of audio data from
+     the waveform, given start and end indices. It checks whether the size of the extracted segment matches
+     the expected size based on the provided start and end indices and the sample rate.
+
+     Returns:
+            None
+
+
+    """    
+  
+    start = 4
+    end = 7
+    assert AudioProcessor(TEST_WAVEFORM, TEST_SR).cut(start, end).size() == int((end - start) * TEST_SR)
+
+
+
+
+   
+
+
+
+
+
+def test_audio_processor_invalid_sr():
+    """Test the behavior of AudioProcessor when an invalid smaple rate is provided.
+    
+    This test verifies that the AudioProcessor constructor raises a ValueError when an invalid sample rate is provided. It uses the pytest.raises context manager to check if the ValueError is raised when initializing an 
+    AudioProcessor object with an invalid sample rate.
+
+    Returns:
+           None
+    """    
+    with pytest.raises(ValueError):
+        AudioProcessor(TEST_WAVEFORM, [44100,48000])
+
+
+def test_audio_processor_SAMPLE_RATE():
+    """Test the default sample rate of the AudioProcessor class.
+    
+    This test verifies that the default sample rate of the AudioProcessor class matches the expected value defined by the constant SAMPLE_RATE. It instantiates an AudioProcessor object with a test waveform
+    and checks whether the sample rate attribute (sr) of the AudioProcessor object equals the predefined constant SAMPLE_RATE.
+
+    Returns:
+           None
+    """    
+    probe_audio_processor = AudioProcessor(TEST_WAVEFORM)
+    assert probe_audio_processor.sr == SAMPLE_RATE       
+
+
+
+
+
+
+
+
+
+
+
+  
+
+
+    
+
+

test/test_autotranscript.py

@@ -0,0 +1,55 @@
+import pytest
+import torch
+from scraibe import Scraibe, Diariser, Transcriber, Transcript, AudioProcessor
+from unittest.mock import MagicMOck, patch
+
+
+"""
+@pytest.fixture
+def example_audio_file(tmp_path):
+    audio_path = tmp_path 
+"""
+@pytest.fixture
+def create_scraibe_instance():
+    return Scraibe()
+
+
+
+def test_scraibe_init(create_scraibe_instance):
+    model = create_scraibe_instance
+    assert isinstance(model.transcriber, Transcriber)
+    assert isinstance(model.diariser, Diariser)
+
+
+def test_scraibe_autotranscribe(create_scraibe_instance, example_audio_file):
+    model = create_scraibe_instance
+    transcript = example_audio_file
+    assert isinstance(transcript, Transcript)
+
+def test_scraibe_diarization(create_scraibe_instance, example_audio_file):
+    model = create_scraibe_instance
+    diarisation_result = model.diarisation(example_audio_file)
+    assert isinstance(diarisation_result, dict)
+
+
+def test_scraibe_transcribe(create_scraibe_instance, example_audio_file):
+    model = create_scraibe_instance
+    transcription_result = model.transcribe(example_audio_file)
+    assert isinstance(transcription_result, str)
+
+
+def test_remove_audio_file(create_scraibe_instance, example_audio_file):
+    model = create_scraibe_instance
+    with pytest.raises(ValueError):
+        model.remove_audio_file("non_existing_audio_file")
+
+    model.remove_audio_file(example_audio_file)
+    assert not os.path.exists(example_audio_file)      
+
+
+def test_get_audio_file(create_scraibe_instance, example_audio_file):
+    model = create_scraibe_instance
+    audio_file = os.path.exist(example_audio_file)
+    assert isinstance(audio_file, AudioProcessor)
+    assert isinstance(audio_file.waveform, torch.Tensor)
+    assert isinstance(audio_file.sr, torch.Tensor)

test/test_diarisation.py

@@ -0,0 +1,61 @@
+import pytest
+import os
+from unittest import mock
+from scraibe import Diariser
+
+
+
+@pytest.fixture
+def diariser_instance():
+    """Fixture for creating an instance of the Diariser class with mocked token.
+
+    This fixture is used to create an instance of the the Diariser class with a mocked token returned by the _get_token method. It patches the _get_token method of the Diariser class
+    using unit.test.mock.patch.object, ensuring that it returns a predetrmined value ('personal Hugging-Face token'). The mocked Diariser object is retunrned and can be used as a dependency in otehr tests.
+
+    Returns:
+        Diariser(Obj): An instance of the Diariser class with a mocked token.
+    """
+    with mock.patch.object(Diariser, '_get_token', return_value = 'personal Hugging-Face token')
+        return Diariser('pyannote')
+
+
+
+def test_Diariser_init(diariser_instance):
+    """Test the initialization of the Diariser class.
+
+    This test verifies that the Diariser class is correctly initialized with the specified model.
+    It checks whether the 'model' attribute of the instantiated Diariser object equals 'pyannote'.
+
+
+    Args:
+        diariser_instance (obj): instance of the Diariser class
+
+    Returns: 
+           None
+    """    
+    assert diariser_instance.model == 'pyannote'
+
+
+
+def test_diarisation_function(diariser_instance):
+    """Test the diarization function of the Diariser class.
+
+    This test verifies that the diarization function of the Diariser class correctly processes
+    an audio file and returns the diarization result. It patches the apply method of the model
+    attribute of the Diariser instance using unittest.mock.patch.object, ensuring that it returns 
+    a predetermined value ('diarization_result') when called with the audio file argument.
+    It then calls the diarization function with an example audio file and checks whether the returned 
+    diarization output matches the expected result ('diarization_result').
+
+    Args:
+        diariser_instance (obj): instance of the Diariser object
+
+    Returns:
+        None    
+    """    
+    with mock.patch.object(diariser_instance.model, 'apply', return_value='diarization_result'):
+        diarization_output = diariser_instance.diarization('example_audio_file.wav')
+        assert diarization_output == 'diarization_result'
+
+
+

test/test_transcriber.py

@@ -0,0 +1,29 @@
+import pytest
+from unittest.mock import patch
+from scraibe import Transcriber
+
+
+
+
+@pytest.mark.parametrize("audio_file, expected_transcription",[("path_to_test_audiofile", "test_transcription")] )
+@patch("scraibe.Transcriber.load_model")
+
+def test_transcriber(mock_load_model, audio_file, expected_transcription):
+    """_summary_
+
+    Args:
+        mock_load_model (_type_): _description_
+        audio_file (_type_): _description_
+        expected_transcription (_type_): _description_
+    """    
+    mock_model = mock_load_model.return_value
+    mock_model.transcribe.return_value ={"text": expected_transcription} 
+
+    transcriber = Transcriber.load_model(model="medium")
+
+    transcription_result = transcriber.transcribe(audio=audio_file)
+
+    assert transcription_result == expected_transcription
+
+
+