search

ranchlai / mandarin-tts

Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei and aishell3 datasets
465 stars 111 forks source link

Runtime Error: Error in loading state_dict for FastSpeech2 #4

Open LifaSun opened 3 years ago

LifaSun commented 3 years ago

@ranchlai 感谢分享！按照readme，一步一步运行会报错：

loading model from ./checkpoint/checkpoint_500000.pth Traceback (most recent call last): File "synthesize.py", line 123, in model = build_model().to(device) File "synthesize.py", line 50 in build_model model.load_state_dict(sd) File "/usr/local/lib/....../module.py， line 1224, in load_state_dict

Runtime Error: Error in loading state_dict for FastSpeech2

Miss key(s) in state_dict: "decoder.speaker_fc.weight" size mismatch for encoder.position_enc: copyinga param with shape torch.size([1, 10 01，256]) from checkpiont, the shape in current model is torch.size([1, 2001, 256])。 size mismatch for encoder.src_word_emb.weight: copying a param with shape torch.size ([1612，256])Erom checkpoint,the shape in current model is torch.size([1915，256])。 size mismatch for encoder.cn_word_emb.weight: copying a param with shape torch.size( [4135，2561)From checkpoint, the shape in current model is torch.size([4502，256])。 size mismatch for decoder.position_enc: copyinga param with shape torch.size([1, 10 01，2561) from checkpoint,the shape in current model is torch.size([1, 2001, 256])/content/

Thanks!

ranchlai commented 3 years ago

please use this commit： c008dd766d4c72709864df6d41854b44ccf96eea git reset c008dd766d4c72709864df6d41854b44ccf96eea

LifaSun commented 3 years ago

Thanks!

cui7616 commented 3 years ago

碰到了同样的问题，没明白怎么修改？

zhibin86 commented 3 years ago

Hey, I got the same issue. Can you tell me how to fix it. Thanks a lot.

_loading model from ./checkpoint/checkpoint_500000.pth Traceback (most recent call last): File "synthesize.py", line 123, in model = build_model().to(device) File "synthesize.py", line 50, in build_model model.load_state_dict(sd) File "/home/jingjia/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1044, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for FastSpeech2: Missing key(s) in state_dict: "decoder.speaker_fc.weight". size mismatch for encoder.position_enc: copying a param with shape torch.Size([1, 1001, 256]) from checkpoint, the shape in current model is torch.Size([1, 2001, 256]). size mismatch for decoder.positionenc: copying a param with shape torch.Size([1, 1001, 256]) from checkpoint, the shape in current model is torch.Size([1, 2001, 256]).

Yanshang1991 commented 3 years ago

大佬，我也到这个问题了。要怎么解决？

ranchlai commented 3 years ago

Sorry for late reply. I should fix this error by opening another branch for aishell3 (multispeaker with speaker embedding), but since I don't have enough time, a simple solution to this error is reset to the biaobei version

Solution: 

git clone https://github.com/ranchlai/mandarin-tts.git
cd mandarin-tts
git reset c008dd766d4c72709864df6d41854b44ccf96eea --hard
python synthesize.py --input="您的电话余额不足，请及时充值"

It should work

lee9871 commented 3 years ago

大佬，我也到这个问题了，麻烦 能不能说下 我咋直接 改代码，不知道原因是啥

ranchlai commented 3 years ago

旧版本：可使用biaobei分支：git checkout biaobei.

新版本：试试mtts分支，以后只维护这个分支。

YYouFuYuan commented 3 years ago

我也碰到了这个问题，而且用git reset c008dd7也找不到仓库，还有其他解决办法吗