-
Hi @dathudeptrai,
We(@sayakpaul) successfully converted the PyTorch pre-trained model(from the [repository](https://github.com/kan-bayashi/ParallelWaveGAN)) to TFLite Format with the help of [Note…
-
Hi
@monatis below code generates correct audio with [https://www.dropbox.com/s/ixsp0bxck2di4rs/TensorFlowtts.zip?dl=1](url)(from colab) but doesn't with the latest commit f046e824f18b4c7b7db2b65705a6…
-
Hello! First of all, thank you so much for the work: it's incredibile! 🥇
I want to retrain the system on an a different voice, with hours of recordings I will make. In order to achieve so, I was t…
-
ave
 and got this:
```
/usr/local/li…
-
@dathudeptrai Hi, I have a question. Why does the training data loss curve look steady downward when training the fastspeech2 v2 model, but the eval data loss curve oscillates so much?
-
Hi,
Sorry to ask your help once again @mapledxf
I am trying to customise the Android example to use a custom FastSpeech2 model with the MB-MelGan Universal Vocoder.
The problem is, speech is …