Rishikesh (ऋषिकेश)

Need some clarification regarding Reference encoder architecture

1

@yanggeng1995 On paper author mentioned on `ReferenceEncoder` (section 2.2 ) the output of the GRU layers passed through two separate Fully connected layers, but in this implementation, last GRU state...

Does VAE model supports Tacotron 2 ?

5

Nice implementation of VAE tacotron paper though I havn't read paper yet ,but start model training with LJSpeech. As I see this code is extending the Tacotron 1 implementation so...

Getting error for training with Tacotron

14

I have used this (https://github.com/Rayhane-mamah/Tacotron-2) implementation for pre-processing. And when I write command for training `python3 train.py --dataset Tacotron training_data` And getting this error ``` x = torch.cat([x.unsqueeze(-1), mels, a1[:,:,:-1]],...

Can we Wavenet-vocoder for voice synthesis ?

2

Is it possible to integrate this project with wavenet vocoder (https://github.com/r9y9/wavenet_vocoder) and generate voice from spectrogram using parallel wavenet.

VoiceCraft with Parler-TTS's 10K hours speech data

3

Hi @jasonppy Have you look at the Huggingface's Data Speech, a 10k hour of clean curated TTS data : https://huggingface.co/datasets/parler-tts/mls-eng-10k-tags_tagged_10k_generated . I think training the 830M model on this data...

Issue when applying AMP on LSTM

1

Traceback (most recent call last): File "train.py", line 239, in args.warm_start, args.amp, args.name, hp) File "train.py", line 161, in train y_pred = model(x) File "/home/deepsyncv100-1/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result...

Use this model for Voice conversion

11

Hi @adelacvg Can we use this kind model for speech to speech (Voice conversion).