MCPcopy
hub / github.com/coqui-ai/TTS / VitsAudioConfig

Class VitsAudioConfig

TTS/tts/models/vits.py:217–224  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

215
216@dataclass
217class VitsAudioConfig(Coqpit):
218 fft_size: int = 1024
219 sample_rate: int = 22050
220 win_length: int = 1024
221 hop_length: int = 256
222 num_mels: int = 80
223 mel_fmin: int = 0
224 mel_fmax: int = None
225
226
227##############################

Callers 9

train_yourtts.pyFile · 0.90
train_vits_tts.pyFile · 0.90
train_vits_tts_phonemes.pyFile · 0.90
train_vits.pyFile · 0.90
train_yourtts.pyFile · 0.90
train_vits.pyFile · 0.90
train_vits.pyFile · 0.90
test_train_step_upsamplingMethod · 0.90
test_train_step_upsampling_interpolationMethod · 0.90

Calls

no outgoing calls

Tested by 2

test_train_step_upsamplingMethod · 0.72
test_train_step_upsampling_interpolationMethod · 0.72

Used in the wild real call sites across dependent graphs

searching dependent graphs…