Chinese-FastSpeech2

Chinese-FastSpeech2 copied to clipboard

在使用biaobei.py里的get_char_embedding_from_bert生成expanded_embeds.pkl时显示如下，该怎么解决呀？ size mismatch for bert.embeddings.position_embeddings.weight: copying a param with shape torch.Size([512, 1024]) from checkpoint, the shape in current model is torch.Size([512, 768]).

Bingtai1015

UP主有用这个项目训练多个模型没？我再想用之前训练的模型调用synthesize.py时就会报这个异常，对这个不熟悉的我真的难到了，万望UP主试一下看看能不能使用之前的模型，先行谢过。

fangg2000

有英文的韵律增强吗

1

您好，请问有英文训练的prosody bert做韵律增强吗？例如ljspeech, libritts

rechawine

About fine-tuning issues.

1

I plan to fine-tune my own dataset based on the AISHELL3 model, but my dataset only has 6 speakers, while AISHELL3 has 218. When loading the model, an error occurred...

ltydd