Spaces:
Sleeping
Sleeping
File size: 2,600 Bytes
e11256b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import pytest
from scraibe import (Transcriber, WhisperTranscriber,
FasterWhisperTranscriber, load_transcriber)
import torch
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
TEST_WAVEFORM = "Hello World"
"""
@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):
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 """
@pytest.fixture
def whisper_instance():
return load_transcriber('tiny', whisper_type='whisper')
@pytest.fixture
def faster_whisper_instance():
return load_transcriber('tiny', whisper_type='faster-whisper')
def test_whisper_base_initialization(whisper_instance):
assert isinstance(whisper_instance, Transcriber)
def test_faster_whisper_base_initialization(faster_whisper_instance):
assert isinstance(faster_whisper_instance, Transcriber)
def test_whisper_transcriber_initialization(whisper_instance):
assert isinstance(whisper_instance, WhisperTranscriber)
def test_faster_whisper_transcriber_initialization(faster_whisper_instance):
assert isinstance(faster_whisper_instance, FasterWhisperTranscriber)
def test_wrong_transcriber_initialization():
with pytest.raises(ValueError):
load_transcriber('tiny', whisper_type='wrong_whisper')
def test_get_whisper_kwargs():
kwargs = {"arg1": 1, "arg3": 3}
valid_kwargs = Transcriber._get_whisper_kwargs(**kwargs)
assert not valid_kwargs == {"arg1": 1, "arg3": 3}
def test_whisper_transcribe(whisper_instance):
model = whisper_instance
# mocker.patch.object(transcriber_instance.model, 'transcribe', return_value={'Hello, World !'} )
transcript = model.transcribe('tests/audio_test_2.mp4')
assert isinstance(transcript, str)
def test_faster_whisper_transcribe(faster_whisper_instance):
model = faster_whisper_instance
# mocker.patch.object(transcriber_instance.model, 'transcribe', return_value={'Hello, World !'} )
transcript = model.transcribe('tests/audio_test_2.mp4')
assert isinstance(transcript, str)
|