KnowBetterHelps

I mean the input is one sentence, and there are some homograph words in it, I want to get the right pronunciation of ever word in the sentence

The same question I want to ask,too. In my case, use librosa.feature.melspectrogram and then to compute librosa.feature.mfcc is not equal with kaldi's process. BTW, did you find the way to...

thank you for your kind reply I will looking for it

I also have this problem, and I tried a lot of ways, still cannot work, did you solved this? Matplotlib required for plot() Traceback (most recent call last): File "/home/huyuezhi/tts-train/deng/train-tts-voicenet/voicenet-master/src/run_tts.py",...

hi, when I run the code with my own data（child voice data），it always get the bug"magphase.py:352: RuntimeWarning: invalid value encountered in divide", is there anything I did wrong?

maybe you should check file _"exp/train_in240_hidden256_e3_lstm_drop0.2_dot_emb512_hidden512_d1_epoch20_norm5_bs32_mli800_mlo150_adam_lr1e-3_mmt0_l21e-5_delta/decode_test_beam30_nbest1_ml100/data.json"_ ?

yeah, it should be generated when decoding started I am running the training proccessing now, and it will be finished tomorrow, I'll see it whether got the same problem.

I found the same problem, but the main reason is not "the file non exist". in my case, I found a encoding error in _"exp/train_in240_hidden256_e3_lstm_drop0.2_dot_emb512_hidden512_d1_epoch20_norm5_bs128_mli800_mlo150_adam_lr1e-3_mmt0_l21e-5_delta/decode_test_beam30_nbest1_ml100/decode.log"_ I use "export PYTHONIOENCODING=UTF-8" to...

yes, I am waiting for decoding finished now. recognition result seems okay

I guess: 1、it is not correct for you to copy _*test/data.json*_ to _*exp/{...}/data.json*_. if you do so, the score script would compare _*test/data.json*_ with _*exp/{...}/data.json*_, which are the same in...