训练总是空跑

[wuzhengxuan]

音频是15s一个文件 格式是FormatFactoryPart1 文本预处理和生成bert都成功了，但是训练总是空跑，信息如下

加载config中的配置0 加载config中的配置localhost 加载config中的配置10086 加载config中的配置0 加载config中的配置1 加载环境变量 MASTER_ADDR: localhost, MASTER_PORT: 10086, WORLD_SIZE: 1, RANK: 0, LOCAL_RANK: 0 01-01 22:51:58 INFO | data_utils.py:63 | Init dataset... 100%|███████████████████████████████████████████████████████████████████████████████| 97/97 [00:00<00:00, 96226.94it/s] 01-01 22:51:58 INFO | data_utils.py:78 | skipped: 77, total: 97 Bucket warning 01-01 22:51:58 INFO | data_utils.py:63 | Init dataset... 100%|████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<?, ?it/s] 01-01 22:51:58 INFO | data_utils.py:78 | skipped: 3, total: 4 Using noise scaled MAS for VITS2 Using duration discriminator for VITS2 INFO:models:Loaded checkpoint 'Data\xybb\models\DUR_0.pth' (iteration 0) ERROR:models:emb_g.weight is not in the checkpoint INFO:models:Loaded checkpoint 'Data\xybb\models\G_0.pth' (iteration 0) INFO:models:Loaded checkpoint 'Data\xybb\models\D_0.pth' (iteration 0) **检测到模型存在，epoch为 1，gloabl step为 0***** INFO:models:Loaded checkpoint 'Data\xybb\models\WD_0.pth' (iteration 0) 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. 0it [00:07, ?it/s] INFO:models:====> Epoch: 0 0it [00:00, ?it/s] INFO:models:====> Epoch: 1 0it [00:00, ?it/s] INFO:models:====> Epoch: 2 0it [00:00, ?it/s] INFO:models:====> Epoch: 3

请问该如何是好

[YYuX-1145]

被跳过了那么多，数据集有大问题

[wuzhengxuan]

被跳过了那么多，数据集有大问题

您是指音频的格式有问题？还是？我看文本预处理的信息大部分都是对的

[YYuX-1145]

数据集质量，包括标注和清晰度等 被跳那么多条说明数据集制备有问题

[wuzhengxuan]

数据集质量，包括标注和清晰度等 被跳那么多条说明数据集制备有问题

明白了，我再整理整理，非常感谢