Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Deepvoice training #57

Open
hansolc opened this issue Nov 2, 2018 · 1 comment
Open

Deepvoice training #57

hansolc opened this issue Nov 2, 2018 · 1 comment

Comments

@hansolc
Copy link

hansolc commented Nov 2, 2018

현재 single모델로 손석희 모델은 트레이닝을 성공한 상태 이구요
제가 다른 음성 데이터가 적어서 손석희 데이터를 통해 다른 목소리로 트레이닝을 해보려고 deepvoice 로 훈련을
시켰는데 step은 진행 되지만 synthesizer.py 을 통해 음성을 만드는 부분에서 알 수 없는 오류가 나와 질문 드립니다.

Constructing model: tacotron
UPDATE model_type: single -> deepvoice
Traceback (most recent call last):
File "synthesizer.py", line 383, in
synthesizer.load(config.load_path, config.num_speakers, config.checkpoint_step)
File "synthesizer.py", line 52, in load
self.num_speakers, speaker_id)
File "/home/hs/jongsul/multi-speaker-tacotron-tensorflow/models/tacotron.py", line 189, in initialize
for idx, cell in enumerate(decoder_rnn_init_states):
TypeError: 'NoneType' object is not iterable

이와 같이 데이터가 없다고 나오는데 왜그런지 알 수 있을까요??

@freds0
Copy link

freds0 commented Mar 27, 2019

Try passing the parameter --num_speakers=2 to the synthesizer.py script. It works for me.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants