Ellie Kang
Thank you for your great project for Korean speech. In updated version v.1.3, there is no transcript regarding 1/1_1005.wav file. I think it's normal wav file and sampled well as...
I encountered dimension error after finishing epoch 1. [02/12/2019 03:42:48] (Tv, epoch: 1, it: 373/2194, t/smpl: 0.031s) g_fake:0.000 g_cond:0.000 g_mskd_fake:-0.087 g_mskd_cond:2.259 g_cyc:0.014 g_rgb:0.000 g_rgb_un:0.000 g_rgb_s:0.000 g_m1:0.100 g_m2:0.100 g_m1_s:0.002 g_m2_s:0.002 g_idt:0.000...
from theano.tensor.signal import downsample I think it's from theano and lasagne version problem But it's not solved when I enter pip install --upgrade https://github.com/Theano/Theano/archive/master.zip pip install --upgrade https://github.com/Lasagne/Lasagne/archive/master.zip
First, thank you for a great project with data in multiple languages for persona chat. The reference link to the XNLG mentioned is well explained, but I will write it...
안녕하세요:) 맥환경과 우분투환경에서 load가 되지 않아 ValueError: model_drama.bin has wrong file format! 에러가 뜹니다. 파일에 문제가 있다면 새롭게 업로드해주실 수 있을까요? https://fasttext.cc/docs/en/crawl-vectors.html 에서 한국어 pretrained model을 이용한 후 [파이썬과](https://github.com/keras-team/keras/issues/9595#issuecomment-459218014) tf,keras...
Thank you for your project and I am actually working on converting waveglow code into Tensorflow. For quick training allignment during fine-tuning, I am thinking of converting pytorch model into...
Thank you for great repository Is there any available pretrained model??
usage
Thank you for great work done I was following on speech.ko repo to preprocess, deep speech.pytorch repo with preprocess, preparemetafile . I was wondering if this repo is independent to...
타코트론 모델 훈련 후 generate.py를 실행하면 sess.run(net.queue_initializer) # 이 부분이 없으면, checkpoint에서 복원된 값들이 들어 있다. 이 코드부분에서 에러가 발생합니다. FailedPreconditionError (see above for traceback): Attempting to use uninitialized value...