I cannot proceed with training(JP-Extra) due to an error.

[Enchante503]

I cannot proceed with training(JP-Extra) due to an error.
The pre-processing step is completed successfully.

Environment:
WSL2　Ubuntu 22.04.4 LTS
Python 3.10.6
torch 2.3.1+cuda12.1
numpy 1.23.5

11-22 21:00:23 |  INFO  | default_style.py:54 | At least 2 subdirectories are required for generating style vectors with respect to them, found 0.
11-22 21:00:23 |  INFO  | default_style.py:57 | Generating only neutral style vector instead.
11-22 21:00:23 |  INFO  | default_style.py:28 | Saved mean style vector to model_assets/test
11-22 21:00:23 |  INFO  | default_style.py:36 | Saved style config to model_assets/test/config.json
11-22 21:00:23 |WARNING | __init__.py:247 | /home/user/Style-Bert-VITS2/style_bert_vits2/models/utils is not a git repository, therefore hash value comparison will be ignored.
11-22 21:00:23 |  INFO  | data_utils.py:69 | Init dataset...
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 47259.76it/s]
11-22 21:00:23 |  INFO  | data_utils.py:84 | skipped: 0, total: 4
11-22 21:00:23 |  INFO  | data_utils.py:69 | Init dataset...
0it [00:00, ?it/s]
11-22 21:00:23 |  INFO  | data_utils.py:84 | skipped: 0, total: 0
11-22 21:00:23 |  INFO  | train_ms_jp_extra.py:274 | Using noise scaled MAS for VITS2
11-22 21:00:25 |WARNING | safetensors.py:42 | Missing key: enc_p.style_proj.weight
11-22 21:00:25 |WARNING | safetensors.py:42 | Missing key: enc_p.style_proj.bias
11-22 21:00:25 |WARNING | safetensors.py:42 | Missing key: emb_g.weight
11-22 21:00:25 |  INFO  | safetensors.py:48 | Loaded 'Data/test/models/G_0.safetensors'
11-22 21:00:26 |  INFO  | safetensors.py:48 | Loaded 'Data/test/models/D_0.safetensors'
11-22 21:00:26 |  INFO  | safetensors.py:48 | Loaded 'Data/test/models/WD_0.safetensors'
11-22 21:00:26 |  INFO  | train_ms_jp_extra.py:492 | Loaded the pretrained models.
11-22 21:00:26 |  INFO  | train_ms_jp_extra.py:540 | Start training.
  0%|                                                                                                                                   | 0/200 [00:00<?, ?it/s]

ERROR  | subprocess.py:33 | Error: train_ms_jp_extra.py --config Data/test/config.json --model Data/test --not_use_custom_batch_sampler
Some weights of the model checkpoint at ./slm/wavlm-base-plus were not used when initializing WavLMModel: ['encoder.pos_conv_embed.conv.weight_g', 'encoder.pos_conv_embed.conv.weight_v']
- This IS expected if you are initializing WavLMModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing WavLMModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of WavLMModel were not initialized from the model checkpoint at ./slm/wavlm-base-plus and are newly initialized: ['encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'encoder.pos_conv_embed.conv.parametrizations.weight.original1']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

[gordon0414]

I think the Error message is truncated. Can you provide me more Error messages if possible?
Btw, from my personal experiences, maybe go check the config.json of the Data/{your_model}/ to see if "use_jp_extra" is true