glow-tts

glow-tts copied to clipboard

멀티 GPU를 사용하지 않고 학습하는 과정에서 에러가 발생합니다. 따라서 DDI 관련된 세팅을 False로 전환하여 학습을 했습니다. 이때 학습이 되지 않습니다. Loss값이 줄어 들는 것을 확인 했지만, 오디오를 들어보면 노이즈만 들려오는...

johnny9696

Could not create monotonic_align

3

error: could not create 'monotonic_align/core.cpython-37m-x86_64-linux-gnu.so': No such file or directory

ankurdhuriya

Multi speaker training error

11

Hi, I am trying to train a multi-speaker, but when I run "train.py" I get the following error: ``` INFO:korean_base_2:{'train': {'use_cuda': True, 'log_interval': 20, 'seed': 1234, 'epochs': 10000, 'learning_rate': 1.0,...

kumdori88

Can I apply MAS method to other model ?

1

I'm applying MAS to FastSpeech2 to replace MFA tool. I'm using encoder output in FastSpeech2 as the encoder output in Glow-TTS to fed into MAS method. After several iteration, the...

dohuuphu

aishakhan22

Transfer to tensorRT and using triton inference

7

Does anyone have experience of converting the models into tensorRT and/or using nvidia triton inference container to serve glow tts models?

andrey999333

Error using mel generated from glow-tts for hifi-gan training

1

getting error - **RuntimeError: stack expects each tensor to be equal size, but got [8192] at entry 0 and [8129] at entry 12** Do anyone have a solution to do...

ankurdhuriya

Runtime Error: Multi speaker

1

Hi @jaywalnut310 , I've the following configuration for multi-speaker and I am getting the below error. I've done all other necessary changes as highlighted here in different posts like changing...

ppanja

ImportError: /glow-tts/monotonic_align/monotonic_align/core.cpython-38-x86_64-linux-gnu.so: failed to map segment from shared object

1

ImportError: /glow-tts/monotonic_align/monotonic_align/core.cpython-38-x86_64-linux-gnu.so: failed to map segment from shared object How to solve this error/issue? I have followed the prerequisite steps only except I haven't put waveglow pre-trained model into waveglow...

tabhishek432

Sharing my results. Glow-tts is incredibly impressive!

5

Thank you so much for developing such a high-quality, sparse, and performant network, @jaywalnut310. I thought I'd share the results I have obtained so that others can see how promising...

echelon