rubbervduck

Sarabjot Singh 's starred repositories

Awesome-Speech-Enhancement

A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech enhancement and make them universally accessible and useful.

Language:MATLABMIT69200

dla

Deep learning for audio processing

Language:Jupyter NotebookMIT54800

EffectivePyTorch

PyTorch tutorials and best practices.

164200

audacity

Audio Editor

Language:CNOASSERTION1192100

LLM101n

LLM101n: Let's build a Storyteller

2554000

researchpapers

A list of research papers that I have read so far and recommend to other Deep Learning enthusiasts such as myself.

800

Residual-Attention-Network

Keras Implementation Residual Attention Network

Language:Python4000

ResidualAttentionNetwork

A Gluon implement of Residual Attention Network. Best acc on cifar10-97.78%.

Language:PythonMIT10600

ResidualAttentionNetwork-pytorch

a pytorch code about Residual Attention Network. This code is based on two projects from

Language:Python67200

awesome-semantic-segmentation

:metal: awesome-semantic-segmentation

1200

image-segmentation-keras

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

Language:PythonMIT287500

keras-applications

Reference implementations of popular deep learning models.

Language:PythonNOASSERTION500

catalyst

Reproducible and fast DL & RL.

Apache-2.0200

residual_attention_network

Keras implementation of Residual Attention Network

Language:Jupyter NotebookMIT11100

ResNet-Attention-layer-custom-data-set

This is a deep learning network: ResNet with an attention layer that can be used on a custom data set.

Language:PythonLGPL-3.0500

audio_classification

Multi-class audio classification with MFCC features using CNN

Language:Jupyter Notebook2500

gender-audio-classification

A speaker gender classifier. MFC feature engineering and a pre-trained ResNet-50. GradCAM interpretation.

Language:Jupyter NotebookGPL-3.02400

Audio-Classification-using-Deep-Learning

Classifying 10 different categories of Sound using Deep Learning.

Language:Jupyter Notebook2400

deep-listening

Deep Learning experiments for audio classification

Language:Jupyter Notebook14800

soxan

Wav2Vec for speech recognition, classification, and audio classification

Language:Jupyter NotebookApache-2.023400

DeepAudioClassification

Audio classification using Tensorflow

Language:Jupyter Notebook9600

p2pfl

P2P Federated Learning (p2pfl) is a decentralized federated learning library, it allows creating basic federated learning systems on p2p networks using gossip protocols.

Language:PythonGPL-3.05300