kkoutini/PaSST issues and pull requests

#49 - Where is input normalization applied?

Issue - State: open - Opened by Antoine101 10 months ago

#48 - EOF (End Of File) Error on num_workers>0

Issue - State: open - Opened by Rishabh-S1899 10 months ago - 1 comment

#47 - Changing the depth of PASST.

Issue - State: open - Opened by Rishabh-S1899 10 months ago - 1 comment

#46 - .net and .net_swa parameters in .ckpt file

Issue - State: open - Opened by Rishabh-S1899 11 months ago - 1 comment

#45 - From ViT models to audio

Issue - State: open - Opened by Antoine101 11 months ago - 7 comments

#44 - Fixing weights for fine-tuning?

Issue - State: closed - Opened by Antoine101 11 months ago - 2 comments

#43 - Which config can reproduce the results in paper?

Issue - State: open - Opened by diggerdu 11 months ago - 1 comment

#42 - time_new_pos_embed

Issue - State: closed - Opened by Antoine101 12 months ago - 6 comments

#41 - can use on 8k audio ?

Issue - State: open - Opened by herbiel about 1 year ago - 1 comment

#40 - Pre-trained models on ESC-50

Issue - State: open - Opened by Antoine101 about 1 year ago - 3 comments

#39 - Error when trying to pip install repo

Issue - State: closed - Opened by Antoine101 about 1 year ago - 2 comments

#38 - RuntimeError: stft requires the return_complex parameter be given for real inputs

Issue - State: open - Opened by loukasilias about 1 year ago - 3 comments

#37 - Inference on AudioSet

Issue - State: open - Opened by nandacv over 1 year ago - 3 comments

#36 - test my own model

Issue - State: open - Opened by fuguanyu over 1 year ago - 1 comment

#35 - update kd

Pull Request - State: closed - Opened by kkoutini over 1 year ago

#34 - 音频事件检测

Issue - State: closed - Opened by fuguanyu over 1 year ago

#33 - Getting started with a custom dataset

Issue - State: open - Opened by OhadCohen97 over 1 year ago - 8 comments

#32 - Migratetopip

Pull Request - State: closed - Opened by kkoutini almost 2 years ago

#31 - Inference Issue

Issue - State: open - Opened by Jerry2001 almost 2 years ago - 2 comments

#30 - difference of fine-tuning the pretrained models

Issue - State: open - Opened by nianniandoushabao almost 2 years ago - 2 comments

#29 - I have a problem. why convert wav to mp3?

Issue - State: closed - Opened by zdj97 about 2 years ago - 3 comments

#28 - setup.py

Issue - State: open - Opened by turian about 2 years ago

#27 - Could not solve for environment specs

Issue - State: open - Opened by turian about 2 years ago - 4 comments

#26 - OpenMic fine-tuned model?

Issue - State: closed - Opened by turian about 2 years ago - 2 comments

#25 - Pretrained models config

Issue - State: open - Opened by dlthdus0611 over 2 years ago - 3 comments

#24 - FSD50K - validating on eval data

Issue - State: closed - Opened by Ludvig-Joborn over 2 years ago - 5 comments

#23 - ImportError: cannot import name 'F1' from 'torchmetrics' (/app/anaconda3/lib/python3.7/site-packages/torchmetrics/init.py)

Issue - State: open - Opened by aiXia121 over 2 years ago - 1 comment

#22 - Is it possible to install the passt with python=3.6?

Issue - State: closed - Opened by Alibabade over 2 years ago - 2 comments

#21 - is `config.dyn_norm` enabled?

Issue - State: closed - Opened by faroit over 2 years ago - 1 comment

#20 - fix urls for 20s and 30s audioset weights

Pull Request - State: closed - Opened by kkoutini over 2 years ago

#19 - RuntimeError: The size of tensor a (2055) must match the size of tensor b (99) at non-singleton dimension 3

Issue - State: closed - Opened by 980202006 over 2 years ago - 3 comments

#18 - The loop in the diagram

Issue - State: open - Opened by YangYangTaoTao over 2 years ago - 1 comment

#17 - Installation issues

Issue - State: open - Opened by p4vlos almost 3 years ago - 1 comment

#16 - mismatch version of pytorch-lighting and sarced

Issue - State: open - Opened by Junglesl almost 3 years ago - 15 comments

#15 - Is it possible to use this project directly for a code example for instrument recognition?

Issue - State: closed - Opened by 980202006 almost 3 years ago - 4 comments

#14 - Fine tuning on novel dataset

Issue - State: open - Opened by beyondbeneath almost 3 years ago - 4 comments

#13 - kaggle

Issue - State: open - Opened by woozi1122 almost 3 years ago - 2 comments

#12 - Inference ESC-50 fine-tuned model

Issue - State: closed - Opened by myatmyintzuthin almost 3 years ago - 2 comments

#11 - Wavmix for the ESC50 dataset

Issue - State: open - Opened by Jimmy2027 almost 3 years ago - 1 comment

#10 - Changing tdim for pretrained model

Issue - State: closed - Opened by ranjith1604 almost 3 years ago - 3 comments

#9 - OpenMic2018

Issue - State: open - Opened by adey2021 almost 3 years ago - 1 comment

#8 - The meaning of "swa"

Issue - State: open - Opened by xianyi11 almost 3 years ago - 1 comment

#7 - Openmic2018

Issue - State: open - Opened by WangHelin1997 about 3 years ago - 1 comment

#6 - audio inference

Issue - State: open - Opened by dagongji10 about 3 years ago - 3 comments

#5 - Longer input?

Issue - State: closed - Opened by zelaki about 3 years ago

#4 - Binarizing linear predictions

Issue - State: open - Opened by anarsultani97 about 3 years ago - 1 comment

#3 - Evaluate my own model

Issue - State: closed - Opened by WangHelin1997 about 3 years ago - 2 comments

#2 - Training Logs

Issue - State: closed - Opened by WangHelin1997 about 3 years ago - 3 comments

#1 - No module named 'ba3l.ingredients'

Issue - State: closed - Opened by kimsojeong1225 about 3 years ago - 5 comments

GitHub / kkoutini/PaSST issues and pull requests