def __init__()

in parler_tts/configuration_parler_tts.py [0:0]

• 18 lines of code
• 9 McCabe index (conditional complexity)

    def __init__(self, vocab_size=1024, prompt_cross_attention=False, **kwargs):
        super().__init__(**kwargs)
        if "text_encoder" not in kwargs or "audio_encoder" not in kwargs or "decoder" not in kwargs:
            raise ValueError("Config has to be initialized with text_encoder, audio_encoder and decoder config")

        text_encoder_config = kwargs.pop("text_encoder")
        text_encoder_model_type = text_encoder_config.pop("model_type")

        audio_encoder_config = kwargs.pop("audio_encoder")
        audio_encoder_model_type = audio_encoder_config.pop("model_type")

        model_version = kwargs.get("transformers_version", None)
        if model_version is not None and Version(model_version) <= Version("4.44.2dev") and use_dac_on_the_hub and audio_encoder_model_type=="dac":
            # here we have to manually change model type if DAC based on transformers version
            audio_encoder_model_type = "dac_on_the_hub"

        decoder_config = kwargs.pop("decoder")

        self.vocab_size = vocab_size
        self.prompt_cross_attention = prompt_cross_attention
        self.text_encoder = AutoConfig.for_model(text_encoder_model_type, **text_encoder_config)
        self.audio_encoder = AutoConfig.for_model(audio_encoder_model_type, **audio_encoder_config)
        self.decoder = ParlerTTSDecoderConfig(**decoder_config)
        self.is_encoder_decoder = True