hifi-gan Search Results

436 results
for hifi-gan

Best match

Best match Most commented Newest Recently updated Least commented Oldest Least recently updated

TensorSpeech/TensorFlowTTS #547

hifigan v1 gradient explosion ？

The number of training steps can be seen from the figure ![2](https://user-images.githubusercontent.com/39238619/115490275-57629180-a290-11eb-8e80-d8be8e071d8f.png) ![1](https://user-images.githubus…

unparalleled-ysj updated 3 years ago
12
NVIDIA/tacotron2 #431

How to generate mel with teacher forcing for further use lik…

Should I just go through the training/validation procedures and write out the y_pred?

blx0102 updated 3 years ago
4
mozilla/TTS #661

[New-Model] HiFi-GAN implementation

@rishikksh20 is kind to integrate his own work into TTS. for more details: https://github.com/rishikksh20/HiFi-GAN

erogol updated 3 years ago
9
jik876/hifi-gan #27

Why does the mel.npy file I trained with the tacotron2 model…

I trained the tacotron2 model to produce mel_**.npy ,but in this model, the error of dimension mismatch is reported `python3 inference_e2e.py --checkpoint_file cp_hifigan-1208-test/g_00036000 Initi…

c9412600 updated 3 years ago
5
maum-ai/assem-vc #3

Which Hi-Fi gan version did you use?

Can you indicate which git repo? Official or unofficial? and the Mel is it still 70-800 or 0-8000? Thanks you

faranaziz updated 3 years ago
3
lturing/tacotronv2_wavernn_chinese #56

您好，请问有测试过合成声音的实时性吗？

合成1s钟的音频大概需要多久呢。

hertz-pj updated 3 years ago
3
jik876/hifi-gan #32

What is the input format?

I've seen a lot of general discussion about inputting generated mels into Hifi-GAN and of course we can see the hparams for mel spectrogram in each config file, but nothing that actually says what the…

prattcmp updated 3 years ago
4
TensorSpeech/TensorFlowTTS #447

Hifi GAN pre-trained model

Can you provide the pre-trained model of Hifi GAN trained on LJSpeech dataset. @dathudeptrai

tulasiram58827 updated 3 years ago
3
jik876/hifi-gan #36

Some questions about training

Hey. Why does the readme say that you need to use GTA mels for fine tuning? I used real spectrograms to train waveglow and parallel wavegan, the authors of which indicated that this method achieves a…

Alexey322 updated 3 years ago
2
BenAAndrew/Voice-Cloning-App #28

'WaveGlow' object has no attribute 'encode'

Running: `synthesize(model, waveglow, text, inflect_engine, graph, audio); print(""); ipd.Audio("audio.wav", rate=22050)` Brings: `AttributeError: 'WaveGlow' object has no attribute 'encode'` …

johnpaulbin updated 3 years ago
3

上一页 1...37 38 39 40 41 42 43...44 下一页

436 results for hifi-gan

436 results
for hifi-gan