helpers/model_init_scripts/init_dummy_model.py [38:67]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        attention_dropout=0.0,
        activation_dropout=0.0,
        pad_token_id=encodec_vocab_size,
        eos_token_id=encodec_vocab_size,
        bos_token_id=encodec_vocab_size + 1,
        num_codebooks=num_codebooks,
    )

    decoder = ParlerTTSForCausalLM(decoder_config)
    decoder.save_pretrained(os.path.join(args.save_directory, "decoder"))

    model = ParlerTTSForConditionalGeneration.from_sub_models_pretrained(
        text_encoder_pretrained_model_name_or_path=text_model,
        audio_encoder_pretrained_model_name_or_path=encodec_version,
        decoder_pretrained_model_name_or_path=os.path.join(args.save_directory, "decoder"),
        vocab_size=t5.vocab_size,
    )

    # set the appropriate bos/pad token ids
    model.generation_config.decoder_start_token_id = encodec_vocab_size + 1
    model.generation_config.pad_token_id = encodec_vocab_size
    model.generation_config.eos_token_id = encodec_vocab_size

    # set other default generation config params
    model.generation_config.max_length = int(30 * model.audio_encoder.config.frame_rate)
    model.generation_config.do_sample = True  # True


    model.config.pad_token_id = encodec_vocab_size
    model.config.decoder_start_token_id = encodec_vocab_size + 1
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



helpers/model_init_scripts/init_model_600M.py [38:66]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        attention_dropout=0.0,
        activation_dropout=0.0,
        pad_token_id=encodec_vocab_size,
        eos_token_id=encodec_vocab_size,
        bos_token_id=encodec_vocab_size + 1,
        num_codebooks=num_codebooks,
    )

    decoder = ParlerTTSForCausalLM(decoder_config)
    decoder.save_pretrained(os.path.join(args.save_directory, "decoder"))

    model = ParlerTTSForConditionalGeneration.from_sub_models_pretrained(
        text_encoder_pretrained_model_name_or_path=text_model,
        audio_encoder_pretrained_model_name_or_path=encodec_version,
        decoder_pretrained_model_name_or_path=os.path.join(args.save_directory, "decoder"),
        vocab_size=t5.vocab_size,
    )

    # set the appropriate bos/pad token ids
    model.generation_config.decoder_start_token_id = encodec_vocab_size + 1
    model.generation_config.pad_token_id = encodec_vocab_size
    model.generation_config.eos_token_id = encodec_vocab_size

    # set other default generation config params
    model.generation_config.max_length = int(30 * model.audio_encoder.config.frame_rate)
    model.generation_config.do_sample = True  # True

    model.config.pad_token_id = encodec_vocab_size
    model.config.decoder_start_token_id = encodec_vocab_size + 1
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -