Iver Jordal
Iver Jordal
Yes, that would be interesting. Re numpy: Yes, but I did the numpy conversion in the julius benchmark as well. Pytorch tensors share memory with numpy arrays when running on...
Yes, I've been using fix_length from librosa to solve the length issue. (`from librosa.util import fix_length`)
Hi keunwoochoi :) Thanks for the appreciation. Sorry for the confusion. Please let me try to explain. `mode` is not the same as `p_mode`. `mode` is about how audio gets...
> What would be the best practice to apply a sequence of augmentation to the examples in a batch while varying the randomized parameters per example? I'm not sure what...
By the way, there is a demo script that applies various transforms in all three modes (per_batch, per_example and per_channel) and writes the results to wav. Listening to these output...
Nice visualization :) Should we add it to readme for now? Feel free to make a pull request. I have not started setting up proper documentation yet.
> * I was trying to make a PR but do you think we should add visualizations whee `p_mode` is `per_example` or `per_channel`? p_mode="per_example" is the most relevant in most...
You're probably right :) Maybe I thought about it briefly when I initially coded it and thought "this is possible, but I'll leave it as a TODO for later".
I'm glad you like it :) If you want to make a contribution, that would be welcome
That sounds like a good solution. Would you like to contribute?