转化后的模型推理出的中文音频不对

[potatoker]

我有一个原本config中是chinese_cleaners的vits模型，原始模型本身推理是正常的，使用https://github.com/weirdseed/vits-ncnn-convert-tool转换后，修改了chinese_cleaners值为zh_ja_mixture_cleaners，然后放入SDcard 在Vits-Android-ncnn APP 中加载之后没有报错，但是在生成后出来的音频是意义不明的奇怪发音。请问这里有什么办法可以追溯一下错误原因吗。我的config 完整为：

{
  "train": {
    "log_interval": 10,
    "eval_interval": 100,
    "seed": 1234,
    "epochs": 10000,
    "learning_rate": 0.0002,
    "betas": [
      0.8,
      0.99
    ],
    "eps": 1e-09,
    "batch_size": 16,
    "fp16_run": true,
    "lr_decay": 0.999875,
    "segment_size": 8192,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0
  },
  "data": {
    "training_files": "final_annotation_train.txt",
    "validation_files": "final_annotation_val.txt",
    "text_cleaners": [
      "zh_ja_mixture_cleaners"
    ],
    "max_wav_value": 32768.0,
    "sampling_rate": 16000,
    "filter_length": 1024,
    "hop_length": 256,
    "win_length": 1024,
    "n_mel_channels": 80,
    "mel_fmin": 0.0,
    "mel_fmax": null,
    "add_blank": true,
    "n_speakers": 1,
    "cleaned_text": true
  },
  "model": {
    "inter_channels": 192,
    "hidden_channels": 192,
    "filter_channels": 768,
    "n_heads": 2,
    "n_layers": 6,
    "kernel_size": 3,
    "p_dropout": 0.1,
    "resblock": "1",
    "resblock_kernel_sizes": [
      3,
      7,
      11
    ],
    "resblock_dilation_sizes": [
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ]
    ],
    "upsample_rates": [
      8,
      8,
      2,
      2
    ],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [
      16,
      16,
      4,
      4
    ],
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "gin_channels": 256
  },
  "speakers": ["\u0078\u0075\u0065\u006c\u0069\u006e\u0067"],
  "symbols": [
    "_",
    "\uff0c",
    "\u3002",
    "\uff01",
    "\uff1f",
    "\u2014",
    "\u2026",
    "\u3105",
    "\u3106",
    "\u3107",
    "\u3108",
    "\u3109",
    "\u310a",
    "\u310b",
    "\u310c",
    "\u310d",
    "\u310e",
    "\u310f",
    "\u3110",
    "\u3111",
    "\u3112",
    "\u3113",
    "\u3114",
    "\u3115",
    "\u3116",
    "\u3117",
    "\u3118",
    "\u3119",
    "\u311a",
    "\u311b",
    "\u311c",
    "\u311d",
    "\u311e",
    "\u311f",
    "\u3120",
    "\u3121",
    "\u3122",
    "\u3123",
    "\u3124",
    "\u3125",
    "\u3126",
    "\u3127",
    "\u3128",
    "\u3129",
    "\u02c9",
    "\u02ca",
    "\u02c7",
    "\u02cb",
    "\u02d9",
    " "
  ]
}