-
-
Hello, thank you for your work. I have a question, what is the purpose of masking in your work? As I assume, this is not for hiding future steps, due to FastSpeech2 is non-autoregressive.
-
Hi, i just fast implemented FastSpeech2 to check the contribution of F0 embedding and Energy embedding. See PR #45 for detail.
-
after data preprocessing, I run train_fastspeech2.py but there is no duration file in /dump/train
-
Hello, @dathudeptrai
First of all, I'd like to thank you due to your awesome works.
I've learned a lot from your repos.
Seeing your repos, I got a question regarding f0 and energy estimation.
…
-
Hi, when I update lasted When I pulled the latest code (two hours ago), a data loading error occurred during training fastspeech2
[train]: 0%| …
-
I used the code [here](https://colab.research.google.com/drive/1HudLLpT9CQdh2k04c06bHUwLubhGTWxA?usp=sharing#scrollTo=mKvX8awTaRRs) , saved the .h5 model to tflite model then inference, but this error…
-
Currently i am trying to train my model with Multispeaker dataset. What are the changes I need to apply in the model for training it on fastspeech2?
-
Hello,
First of all, thank you very much for making this library available. It's great!
I have a few questions regarding your Fastspeech 2 implementation:
1. What is used to obtain the word s…
-
I've downloaded LJSpeech, preprocessed, normalized, extracted durations, and set up for finetuning. I have a dataset for a different voice to do transfer learning, but I was getting poor results, so a…