Need help pls

Hello I am unaware if this is normal behavior but whenever I train Tacotron the line model = load_model(hparams) in train.py takes upwards of 30 minutes to execute. has anyone else encountered this behavior.

WARNING: Tensorflow 1 is deprecated, and support will be removed on August 1, 2022. After that, %tensorflow_version 1.x will throw an error. Your notebook should be updated to use Tensorflow 2. See the guide at https://www.tensorflow.org/guide/migrate#migrate-from-tensorflow-1x-to-tensorflow-2.

I'm trying to comprehend how does deep learning in speech synthesis work. The plots below are generated using Tacotron 2 after speech synthesis on my own pretrained model. Left one is typical mel spectrogram, middle one is same but run with postnet and the 3rd one is just alignment graph. Anyone co...

Can anyone pls help me understand how the check points of LJ Speech which is essentially English language, can be used to fine tune any language. I used it for Kannada which is no where close to English yet could get better result. Someone pls throw some light on this. Thanks.

I have trained the tacotron2 in V100S(32GB)， batch_size=114 for filling memory, but can't achieve the 17604(https://lambdalabs.com/gpu-benchmarks); I calculate the throughput roughly by: 114*159 / 3.08 = 5885.065, could you give me some advices? Thank you very much!

我在训练采用标贝数据集 基于pytorch的中文语音合成baseline，目前尝试了拼音建模（字母编码转sequence），batch size 设为32，采样率为48000。目前训练57k个step后，loss已经不再下降，但完全没有对齐，inference结果也不对。请问可能是什么原因，应该如何调整呢？ In the training, I use the biaobei dataset and modif...

I think first checkpoint for transfer learning should sound like pre-trained model,But the model sound gets noisy and pronouciation is a bit fuzzy. both sampling rate is 22KHz Can anybody help ? Thanks.

I am trying to train a model on a data set that employs a significant number of domain specific acronyms. After digging through the issues here it is still unclear to me the best way to do this. Should I be pre-processing strings in the training .txt file to replace them with ARPAbet characters, jus...

follow each step put the changed the batch size to 5-6 since I'm only using 9 wav files. Did everything after this until "Start training!" where I got this error: FP16 Run: False Dynamic Loss Scaling: True Distributed Run: False cuDNN Enabled: True cuDNN Benchmark: False % Total % Received % Xfer...