EfficientAT
EfficientAT copied to clipboard
fschmid56
This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
Firstly I would like to state that this repo is great, so many models, all in pytorch and getting them to work on my machine was very easy. Have you...
Hi, I converted dymn10_as to pytorch mobile, But mobile output is so different with python. I checked both torch version and the model file. What may be the problem? Thanks...
@fschmid56 Thank you for your work! I am looking for ways to detect certain sounds among background noise. would like to check if this method can be used to finetune...
Hello again @fschmid56 , thanks for the awesome repo! I would like to finetune DyMNs on my own dataset for audio classification. Is it possible? If so, would the best...
Hi, first of all, congrats for the amazing job here. I am trying to get predictions of different models but I cannot download directly pretrained models according to the repo:...
Hi! I'm attempting to finetune on openmic, I have the dataset and am running the recommended: ``` python ex_openmic.py --cuda --train --pretrained --model_name=dymn10_as --lr=2e-5 --batch_size=32 ``` I get: ``` Dataset...
Fixed the get_ensemble_model ImportError since it should be imported from models.ensemble rather than models.mn.model
## This pull request introduces two main sets of changes: a new feature for frame-level embedding extraction and several updates to ensure compatibility with modern PyTorch versions by replacing deprecated...
