-
I'm trying to finetune the pretrained Tacotron 2 model on my own (English) dataset.
I follow the steps explained [here](https://github.com/tensorspeech/TensorFlowTTS/tree/master/examples/tacotron2#f…
-
Hello @ZDisket，
where define the tensor name in FastSpeech2.cpp
such as: "serving_default_input_ids" , "serving_default_energy_ratios" ,"StatefulPartitionedCall"
, the authors have implemented multi-speaker models by conditioning on speak…
-
Does it have or is it possible to have a streaming output to reduce sentence latency.
The examples I have seen save complete sentence to file.
I was wondering if a 2 stage buffer could be used w…
-
i'm trying to train a phoneme based FS2 model. I followed all the steps explained in the [libritts](https://github.com/TensorSpeech/TensorFlowTTS/tree/master/examples/fastspeech2_libritts) readme (i a…
-
First thank you, I have solved the issue opened thanks to you support. In my understanding both Melgan (that I have tried) and Waveglow (not run yet) have a female voice. To have a male voice is it ne…
-
Is there a way so see the training metrics/losses of fastspeech2 in TensorBoard?
-
https://github.com/TensorSpeech/TensorFlowTTS/blob/ea72bab6cef40dff68b0b619ecf0d7c9cce3e3f0/tensorflow_tts/models/fastspeech2.py#L123
https://github.com/TensorSpeech/TensorFlowTTS/blob/ea72bab6ce…
-
if i don't want use tacotron2 extract pitch and energy，how to train fastspeech2
wac81 updated
3 years ago