Training data / time - Githubissues

resemble-ai / resemble-enhance

AI powered speech denoising and enhancement

https://huggingface.co/spaces/ResembleAI/resemble-enhance

MIT License

1.32k stars 135 forks source link

Training data / time #3

Open yousifa opened 9 months ago

yousifa commented 9 months ago

Few questions:

How much data was the demo model trained on?
How many epochs?
How long did training take and what system?

AhmadHakami commented 9 months ago

actually there is misinformation in this repository but when I searched for information about the approach and resources they relied on for the model I found this official article, it may help you understand how things work here a little better

4lvrz commented 7 months ago

It seems that the number of training steps is 870000 and the number of trained samples is 192478464. This second number seems to be the total combinations audio+noise+rir trained, so front ground audios could be repeated. You can check this information creating a script loading and printing pretrained models. Training time depends on hardware architecture, so it's dificult to estimate.