def test_in_out(self):
     self._create_random_model()
     config = load_config(
         os.path.join(get_tests_input_path(), 'server_config.json'))
     config['tts_path'] = get_tests_output_path()
     synthesizer = Synthesizer(config)
     synthesizer.tts("Better this test works!!")
Esempio n. 2
0
    def test_common_voice_preprocessor(self):
        root_path = get_tests_input_path()
        meta_file = "common_voice.tsv"
        items = common_voice(root_path, meta_file)
        assert items[0][0] == "Man sollte den Länderfinanzausgleich durch " \
                              "einen Bundesliga-Soli ersetzen."
        assert items[0][1] == os.path.join(get_tests_input_path(), "clips",
                                           "21fce545b24d9a5af0403b949e95e8dd3"
                                           "c10c4ff3e371f14e4d5b4ebf588670b7c"
                                           "9e618285fc872d94a89ed7f0217d9019f"
                                           "e5de33f1577b49dcd518eacf63c4b.wav")

        assert items[-1][0] == "Warum werden da keine strafrechtlichen " \
                               "Konsequenzen gezogen?"
        assert items[-1][1] == os.path.join(get_tests_input_path(), "clips",
                                            "ad2f69e053b0e20e01c82b9821fe5787f1"
                                            "cc8e4b0b97f0e4cab1e9a652c577169c82"
                                            "44fb222281a60ee3081854014113e04c4c"
                                            "a43643100b7c01dab0fac11974.wav")
Esempio n. 3
0
    def test_scaler(self):
        scaler_stats_path = os.path.join(get_tests_input_path(),
                                         'scale_stats.npy')
        conf.audio['stats_path'] = scaler_stats_path
        conf.audio['preemphasis'] = 0.0
        conf.audio['do_trim_silence'] = True
        conf.audio['signal_norm'] = True

        ap = AudioProcessor(**conf.audio)
        mel_mean, mel_std, linear_mean, linear_std, _ = ap.load_stats(
            scaler_stats_path)
        ap.setup_scaler(mel_mean, mel_std, linear_mean, linear_std)

        self.ap.signal_norm = False
        self.ap.preemphasis = 0.0

        # test scaler forward and backward transforms
        wav = self.ap.load_wav(WAV_FILE)
        mel_reference = self.ap.melspectrogram(wav)
        mel_norm = ap.melspectrogram(wav)
        mel_denorm = ap._denormalize(mel_norm)
        assert abs(mel_reference - mel_denorm).max() < 1e-4
Esempio n. 4
0
import os
import unittest

from TTS.tests import get_tests_path, get_tests_input_path, get_tests_output_path
from TTS.utils.audio import AudioProcessor
from TTS.utils.generic_utils import load_config

TESTS_PATH = get_tests_path()
OUT_PATH = os.path.join(get_tests_output_path(), "audio_tests")
WAV_FILE = os.path.join(get_tests_input_path(), "example_1.wav")

os.makedirs(OUT_PATH, exist_ok=True)
conf = load_config(os.path.join(TESTS_PATH, 'test_config.json'))


class TestAudio(unittest.TestCase):
    def __init__(self, *args, **kwargs):
        super(TestAudio, self).__init__(*args, **kwargs)
        self.ap = AudioProcessor(**conf.audio)

    def test_audio_synthesis(self):
        """ 1. load wav
            2. set normalization parameters
            3. extract mel-spec
            4. invert to wav and save the output
        """
        print(" > Sanity check for the process wav -> mel -> wav")

        def _test(max_norm, signal_norm, symmetric_norm, clip_norm):
            self.ap.max_norm = max_norm
            self.ap.signal_norm = signal_norm