helpers/model_init_scripts/init_large_model.py [7:27]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("save_directory", type=str, help="Directory where to save the model and the decoder.")
    parser.add_argument("--text_model", type=str, help="Repository id or path to the text encoder.")
    parser.add_argument("--audio_model", type=str, help="Repository id or path to the audio encoder.")

    args = parser.parse_args()

    text_model = args.text_model
    encodec_version = args.audio_model

    t5 = AutoConfig.from_pretrained(text_model)
    encodec = AutoConfig.from_pretrained(encodec_version)

    encodec_vocab_size = encodec.codebook_size
    num_codebooks = encodec.num_codebooks
    print("num_codebooks", num_codebooks)

    decoder_config = ParlerTTSDecoderConfig(
        vocab_size=encodec_vocab_size + 64,  # + 64 instead of +1 to have a multiple of 64
        max_position_embeddings=4096,  # 30 s = 2580
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



helpers/model_init_scripts/init_model_600M.py [9:29]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("save_directory", type=str, help="Directory where to save the model and the decoder.")
    parser.add_argument("--text_model", type=str, help="Repository id or path to the text encoder.")
    parser.add_argument("--audio_model", type=str, help="Repository id or path to the audio encoder.")

    args = parser.parse_args()

    text_model = args.text_model
    encodec_version = args.audio_model

    t5 = AutoConfig.from_pretrained(text_model)
    encodec = AutoConfig.from_pretrained(encodec_version)

    encodec_vocab_size = encodec.codebook_size
    num_codebooks = encodec.num_codebooks
    print("num_codebooks", num_codebooks)

    decoder_config = ParlerTTSDecoderConfig(
        vocab_size=encodec_vocab_size + 64,  # + 64 instead of +1 to have a multiple of 64
        max_position_embeddings=4096,  # 30 s = 2580
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -