How would one keep the model loaded for immediate synthesis? about flowtron HOT 17 CLOSED

@Bahm9919

server2.zip

This is the continuously running script. If it helps

As for the training... To be honest I'm just winging it based off of the readme file. I still barely understand how the whole system works, let alone specific parameters.

from flowtron.

I've got good results with these steps.

• Train from scratch n_flow2 with my dataset.(17h) Started with n_flow2.
• After i got good attention and val.loss start increasing, started with cummlative attention.
• Cummalative attention gives me more robustness of attention.
• And using checkpoint of cummlative attention to train the voice which i want(only 1.5 hours) with cummlative attention.
• In your case, you can use ljs_pretrained model, and skip first 4 steps, and train with use_cummalative_attn = true n_flows = 2

from flowtron.

Did you solved it? How its going?

from flowtron.

@Bahm9919 More or less, I realized the speaker vecs were what was taking the majority of the time, so I just moved the two mentions of text into the while loop and inference is almost instantaneous.

from flowtron.

@Bahm9919 I realized the answer only a few minutes after I made the post. Although now I am having a different difficulty. I am trying to play the audio live using Python SoundDevice but the output array only reads correctly at 11Khz. And it is badly distorted. I thought the standard sample rate was 22050? Writing the array to a wave file works fine though.

from flowtron.

@Bahm9919 More or less, I realized the speaker vecs were what was taking the majority of the time, so I just moved the two mentions of text into the while loop and inference is almost instantaneous.

How about synthesis with your voice? Did you get good results?

from flowtron.

Not exactly. Any attempt I made with the ljs model had a stuttering problem, so I tried the libritts model with a speaker id of 0. At about 10 or so epochs it starts to sound like me, but allowing it to continue training results in a degradation to static or screams within 10 or 15 more epochs. It’s a little baffling.

from flowtron.

@Bahm9919 I realized the answer only a few minutes after I made the post. Although now I am having a different difficulty. I am trying to play the audio live using Python SoundDevice but the output array only reads correctly at 11Khz. And it is badly distorted. I thought the standard sample rate was 22050? Writing the array to a wave file works fine though.

Yes. But i'm not doing this yet. During 3 months working with this project, training and trying get good results, ive got it only today. Now will try do something like you do.

from flowtron.

Not exactly. Any attempt I made with the ljs model had a stuttering problem, so I tried the libritts model with a speaker id of 0. At about 10 or so epochs it starts to sound like me, but allowing it to continue training results in a degradation to static or screams within 10 or 15 more epochs. It’s a little baffling.

How many flows you did? Did you train n_flow2? did you train with cummulative attention?

from flowtron.

Ok I'll give that a try!

from flowtron.

Ok I'll give that a try!

Fine-tuning which in README didn't work for me. So after done everything, ive trained from scratch the voice which i want. And it gave me better results. However you maybe need more data. I had 1.5h.

from flowtron.

What are the specs of your machine? I am rather limited in processing power at the moment.

from flowtron.

What are the specs of your machine? I am rather limited in processing power at the moment.

I'm using google colab pro)))

from flowtron.

Ahhhhh, I had forgot about the pro account. If I can put together enough training data that might just work! Would you happen to have any colab files you could share?

from flowtron.

Ahhhhh, I had forgot about the pro account. If I can put together enough training data that might just work! Would you happen to have any colab files you could share?

I would like to share, but i don't have, as you mentioned before, you don't understand how these scripts working, but i tell you more, i don't understand nothing with programming. I'm using Inference demo script for inference output.

from flowtron.

Ok Thanks for the advice anyways! I'm sure I can work it out if I spend enough time on it. And if I get the Live inference script cleaned up and working I'll let you know

from flowtron.

Ok Thanks for the advice anyways! I'm sure I can work it out if I spend enough time on it. And if I get the Live inference script cleaned up and working I'll let you know

Thanks for script, I understand your passion. You can write me to telegram @Harmonicas if you need help.

from flowtron.