-
Hi, i found an interested paper (https://arxiv.org/abs/2003.01950) called AlignTTS. With this model maybe we don't need alignment from other models to extract duration for fastspeech anymore. It's gre…
-
I used python to read the content of duration (generated by teacher model transformer), and I found that the length of duration is one more than the length of text. I want to know how to use duration …
-
Hi @dathudeptrai,
I am trying to save fastspeech2 same as fastspeech and it always fails.
Here is my code:
![image](https://user-images.githubusercontent.com/30560413/87169883-e178d500-c2d0-11ea-9b…
-
I tried to convert fastspeech2 to tflite, first I got this error:
from tensorflow_tts.processor.ZAKspeech import symbols, _symbol_to_id
ImportError: cannot import name 'symbols' from 'tensorflow_t…
-
pushed uploaded model which is in assets folder.
not able load model from given path
W/System.err: java.lang.IllegalArgumentException: Contents of /storage/self/primary/fastspeech2_quant.tflite does…
-
-
Will you share android Example using Tacotron2 and MB-Melgan anytime soon?
Thanks
-
I converted the VCTK multiband melgan model which was made from converted weights from kan-bayashi's repo into a SavedModel as detailed in the multiband melgan inference notebook and it works fine in …
-
I am trying to reproduce fastspech2 tarining but when i do this in colab it points to ModuleNotFoundError in training part
but prerpocessing part was succeeded
!CUDA_VISIBLE_DEVICES=0 python /con…
-
After taking trained durations from link at 40k and copying it to dump/train/durations folder I am getting an Indexerror while training the FastSpeeech2
File "/content/TensorflowTTS/examples/fasts…