Felix Burkhardt

I would assume that very often people simply use this package to extract acoustic features per file as opposed to low level features. Problem is that the process_files() method returns...

Thanks for this, it's working well! I wonder is there a possibility to set the minimal pause length between segments? Cheers, Felix

thanks for this awesome list! If you think it's appropriate, I'd be happy to see my 100% Java tool Speechalyzer/Labeltool https://github.com/felixbur/Speechalyzer listed here with "Audio" kindest, Felix

UnicodeEncodeError

8

Getting an lib/python3.9/site-packages/opensmile/core/SMILEapi.py", line 237, in map(lambda v: bytes(str(v), "ascii"), sum(options.items(), ()))) UnicodeEncodeError: 'ascii' codec can't encode character '\u0308' in position 58: ordinal not in range(128) Happened with python3.9 under...

I have a file containing only varied parameters: here are the first three lines (of 720) _varied_params_ f0 av F1 b1 F2 b2 F3 b3 F4 b4 F5 b5 f6...

add to the config file interface that , in all situations were the user has to specify a list, if given a single string this will be interpreted: e.g. ```...

renaming "test" split to "dev"

4

Nkululeko only knows two splits: train and test. but it would be more correct to name the "test" split "dev" (short for development), as we kind of always use it...

export models as onnx

1

instead of pickle, as it's more portable and many ANN models can't be pickeld

Currently, opposed to features, there is no way to combine models. Easiest way would be to try late fusion, i.e. take the output of several models as input of a...