search

lucidrains / naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
MIT License
1.26k stars 100 forks source link

Question about generate speech #19

Open text2speechClone opened 1 year ago

text2speechClone commented 1 year ago

heya my lad, I have run you Usage code for generate speech, but nothing output. Could you please give a full example to accept a prompt and text, then generating the speech? Or give some simple steps to attain this goal.

ggbangyes commented 1 year ago

same question about it

Curlypla commented 1 year ago

"if there is a wip flag next to the title of the repo, it isn't done yet", The model has not yet been trained, so no inference can be made at this stage.

Senpai93 commented 1 year ago

i am just a programmer. i will like to contribute but don't have much knowlage, can you please tell us when can be expect this to start generating some speech. you project is awsome just thanks for open sourcing

deepglugs commented 1 year ago

I was able to train (unconditioned) on some of my data and it was able to produce speech ... but it only one word of speech no matter what. I'll be looking into conditional training soon.

a897456 commented 6 months ago

I was able to train (unconditioned) on some of my data and it was able to produce speech ... but it only one word of speech no matter what. I'll be looking into conditional training soon.

Hi, have you tried something?Can you teach me something: how to use the Usage?Does it need to create a new .py file? Or add a few lines from Usage to my existing encoder?

Linghuxc commented 3 months ago

我能够对部分数据进行（无条件）训练，并且能够生成语音……但无论如何，它只能生成一个单词。我很快就会研究条件训练。

@deepglugs Hello, have you studied conditioning? I found that I couldn't generate hints and text. If you have any relevant experience, please let me know