{
    "version": 2,
    "encoder": {
        "name": "encoder_core",
        "file": "encoder.axmodel",
        "inputs": [
            "cat_tokens"
        ],
        "outputs": [
            "encoded"
        ]
    },
    "decoder_parts": [
        {
            "name": "fm_decoder_part0",
            "file": "decoder_part0.axmodel",
            "inputs": [
                "t",
                "x",
                "text_condition",
                "speech_condition",
                "guidance_scale",
                "padding_mask"
            ],
            "outputs": [
                "decoder_hidden_p0",
                "time_hidden",
                "padding_mask2",
                "cfg_scale"
            ]
        },
        {
            "name": "fm_decoder_part1",
            "file": "decoder_part1.axmodel",
            "inputs": [
                "decoder_hidden_p0",
                "time_hidden",
                "padding_mask2"
            ],
            "outputs": [
                "decoder_hidden_p1"
            ]
        },
        {
            "name": "fm_decoder_part2",
            "file": "decoder_part2.axmodel",
            "inputs": [
                "decoder_hidden_p1",
                "time_hidden",
                "padding_mask2"
            ],
            "outputs": [
                "decoder_hidden_p2"
            ]
        },
        {
            "name": "fm_decoder_part3",
            "file": "decoder_part3.axmodel",
            "inputs": [
                "decoder_hidden_p2",
                "time_hidden",
                "padding_mask2",
                "cfg_scale"
            ],
            "outputs": [
                "v"
            ]
        }
    ]
}