-
1.i notice this stage for fastspeech2 , how to setup /path/to/teacher_dumpdir? dir default is? Specifically tacotron2 model dir?
```
3. Calculate statistics pitch and energy features
./run.sh --s…
wac81 updated
4 years ago
-
First of all thanks for this awesome repository. I have trouble with training FastSpeech2. I trained both Turkish LJSpeech formatted data and directly LJSpeech1.1. According to FastSpeech2 paper, 160k…
-
Hello
We have been trying to train the tacotron2 based speech synthesis model from scratch using the LJSpeech database. Can anyone comment on how long it has taken for them to train this using Cola…
-
```
###################################
# ENGLISH MODELS #
###################################
fs, lang = 22050, "English"
# tag = "kan-bayashi/ljspeech_tacotron2"
# tag = "kan-…
-
Hi Dears,
Thanks for this project.
I train a TTS model on own dataset for Farsi language. I segment an audiobook from one speaker.
I create my dataset like ljspeech and use ljspeech preprocessing, …
-
I used the newest code training a Tacotron2 model with Tensorflow **2.3.1** and want to save it from .h5 model to a PB model, but got this error (Tensorflow **2.2** also got this error):
Traceback …
-
Hi folks.
I am working to make the [TensorFlowTTS_FastSpeech_with_TFLite.ipynb](https://github.com/TensorSpeech/TensorFlowTTS/blob/master/notebooks/TensorFlowTTS_FastSpeech_with_TFLite.ipynb) note…
-
Hi, @Tomiinek . It's a nice job, and it's an honor to see this project.
I have some questions about train.txt; hope you can solve my puzzle.
1. How to get the original train.txt file?
Git clone t…
-
i want train model 'tts_train_conformer_fastspeech2' like model zoo
i use csmsc recipe
i find train_conformer_fastspeech2.yaml, but I can't find the corresponding decode.yaml, just have conf/t…
wac81 updated
4 years ago
-
Hi,
I'm having some difficulties with inference on my FastSpeech2 model. I do not think the speaker IDs at inference correlate with those in `libritts_mapper.json`.
For example, my speakers_map …