google-research/leaf-audio
LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a very small number of parameters.
PythonApache-2.0
Issues
- 0
Conceptual question!
#10 opened by ahmadrv - 2
Training leaf_custom issue!
#9 opened by ahmadrv - 0
How to train LEAF for my dataset?
#23 opened by nazanaza2970 - 0
Ecnoder configuration
#22 opened by yunzqq - 0
- 0
ValueError: Exception encountered when calling layer "audio_classifier" (type AudioClassifier) on mac m1 chip
#20 opened by gta191977649 - 0
Issue on Collab and Kaggle?
#19 opened by jasirnit - 15
Package dependency issue
#2 opened by analogjedi - 0
- 4
requirements
#16 opened by hbl181 - 6
PyTorch Version
#1 opened by snakers4 - 0
@ConvNet Class not Called
#17 opened by sruthisentil - 1
tensorflow-gpu in requirements?
#15 opened by bjarthur - 0
How do I perform audio feature extraction with different window length and inc length?
#14 opened by IrisLhy - 0
Performing audio feature on ESC50 issue!
#13 opened by WuJi1 - 0
Mel filter number and approximation error
#12 opened by mn7ark - 2
- 0
Count number of parameters
#11 opened by JNaranjo-Alcazar - 1
- 0
doh. https://www.leaf-audio.com/
#8 opened by bjarthur - 1
- 0
How to load the weights
#5 opened by goncaloCB - 2
How about the perforemance on ASR task?
#3 opened by SoonSYJ