Closed Crescentz closed 2 years ago
RuntimeError: Error(s) in loading state_dict for DeepSpeech2Model: size mismatch for output.weight: copying a param with shape torch.Size([3894, 1024]) from checkpoint, the shape in current model is torch.Size([6436, 1024]). size mismatch for output.bias: copying a param with shape torch.Size([3894]) from checkpoint, the shape in current model is torch.Size([6436]).
如果是使用预训练模型用于训练,这事这正常的,因为字典不一样,所最后一层的输出大小也不一样。这不是错误。
如果是使用预训练模型用于训练,这事这正常的,因为字典不一样,所最后一层的输出大小也不一样。这不是错误。
用的是你压缩包里的model和vocab.txt
1600小时那个是对的
aishell和thus这两个数据就会有错误
数据集不一样,字典当然不一样
RuntimeError: Error(s) in loading state_dict for DeepSpeech2Model: size mismatch for output.weight: copying a param with shape torch.Size([2988, 1024]) from checkpoint, the shape in current model is torch.Size([3894, 1024]). size mismatch for output.bias: copying a param with shape torch.Size([2988]) from checkpoint, the shape in current model is torch.Size([3894]).