tuong-olli

Hi, Could you help me something about your code? In tacotron.py in line `encoder_outputs = encoder_cell(embedded_inputs, tower_input_lengths[i])`. You add `tower_input_lengths[i]` (this is a tensor) to EncoderRNN (this is a BiLSTM)...

Can't train WaveRNN with voc_mode = 'RAW'

6

I had successfully trained this model with voc_mode = 'MOL' but its synthesized speed is not good. After that, I changed voc_mode from MOL to RAW but it has a...

Can't train with output of Tacotron 2

7

The shape of mel output of Tacotron2 is bigger than mel extracted from audio and the model has issue ``` File "train.py", line 113, in train for i, batch in...

Hello @rishikksh20 , thanks for your sharing. I have some issues in training model. ``` File "/data/tuong/Yen/AdaSpeech/fastspeech.py", line 263, in _forward hs = self.length_regulator(hs, ds, ilens) # (B, Lmax, adim)...

I trained the arctic dataset 180k steps nearly 70hrs with GTX 1080 but the output audio are terrible, un-listenable. Here is my loss graph:  P/S: I...