in docker_images/speechbrain/app/pipelines/text_to_speech.py [0:0]
def __init__(self, model_id: str):
model_type = get_type(model_id)
if model_type is ModelType.TACOTRON2:
self.model = Tacotron2.from_hparams(source=model_id)
self.type = "tacotron2"
elif model_type is ModelType.FASTSPEECH2:
self.model = FastSpeech2.from_hparams(source=model_id)
self.type = "fastspeech2"
else:
raise ValueError(f"{model_type.value} is invalid for text-to-speech")
vocoder_type = get_type(model_id, "vocoder_interface")
vocoder_model_id = get_vocoder_model_id(model_id)
if vocoder_type is ModelType.HIFIGAN:
self.vocoder_model = HIFIGAN.from_hparams(source=vocoder_model_id)
else:
raise ValueError(
f"{vocoder_type.value} is invalid vocoder for text-to-speech"
)
self.sampling_rate = self.model.hparams.sample_rate