-
i have already created durations with MFA, and also ran well two preprocess script(tensorflow-tts-preprocess, tensorflow-tts-normalize) with no error. but when i ran the train script, there is an erro…
-
Thank you for providing such a shocking framework, my work can be reduced a lot. 😊
I got duration data with tacotron pretrained model, when I transfering fastspeech2 with new data, I get it:
```
WA…
-
Hi, thanks for your great work!
I was training this repo on my own dataset.
Everything was OK when I set batch size as `64`. I got training log and checkpoints of model.
But when I tried to increas…
sdc17 updated
4 years ago
-
Hi,
I'm evaluating different techniques for creating speech recognition models that are suitable for use on an Android app.
I'm looking for a way to perform speech-to-text in a real-time, stream…
-
when I run train_fastspeech2 , something is wrong.and I print the shape of [charactor, duration, f0, energy, mel]
> charactor shape is [16, 192]
duration shape is [16, 47]
f0 shape is [16, 47]
e…
-
Hi, I see that your implementation of VariantPredictor is different from source paper's description.
1 the inputs of pitch predictor and energy predictor is outputs from length regulator wh…
-
I am training FS2 on non English Dataset and i have transformed cleaners to "transcilerated_cleaners" and have also changed the valid letters used .
while Training I am incurring error , 2 possible …
-
In egs2/ljspeech/tts1, run.sh succeeded with tuning/train_tacotron2.yaml config, but it caused the following error with conf/tuning/train_fastspeech2.yaml.
Traceback (most recent call last):
Fil…
-
Hello, Thanks for providing the fastspeech2 implementation in espnet2. I am getting the following error when trying to run fastspeech2. I am actually not sure how the phoneme durations are provided in…
-
Hello, I find an interested paper(https://arxiv.org/pdf/2006.04558.pdf) called FastSpeech2. It is an advanced version of FastSpeech, which eliminates the teacher model and directly combines PWG trai…