JorgeRuizDev/SpotMyFM

Issues

• Finish the Readme

  #158 opened 3 years ago by JorgeRuizDev
  0

• Document the software development plan

  #157 opened 3 years ago by JorgeRuizDev
  0

• Finish the design and requirements

  #156 opened 3 years ago by JorgeRuizDev
  0

• Update the Landing Page

  #142 opened 3 years ago by JorgeRuizDev
  0

• Fix wrong css generation

  #148 opened 3 years ago by JorgeRuizDev
  0

• Docker Compose SpotMyFM with DynamoLocal + Bowie + Ludwig

  #127 opened 3 years ago by JorgeRuizDev
  0

• Dockerize + Deploy the nextjs api in GCP RUN

  #141 opened 3 years ago by JorgeRuizDev
  0

• Create a system view with figma

  #149 opened 3 years ago by JorgeRuizDev
  0

• Publish the GTZAN Extended & Ludwig Datasets to Kaggle

  #152 opened 3 years ago by JorgeRuizDev
  0

• Memoir: Introduction

  #153 opened 3 years ago by JorgeRuizDev
  0

• Memoir: Techniques / Technologies / Libraries / Dependencies

  #151 opened 3 years ago by JorgeRuizDev
  0

• Memoir: Objectives

  #150 opened 3 years ago by JorgeRuizDev
  0

• Theoretical concepts

  #146 opened 3 years ago by JorgeRuizDev
  0

• Write a User Manual

  #129 opened 3 years ago by JorgeRuizDev
  0

• Write Programmer Manual

  #155 opened 3 years ago by JorgeRuizDev
  0

• Implement an OVA model for main genre and mood classification

  #118 opened 3 years ago by JorgeRuizDev
  0

• Remove Reggae as a main genre and add it as a latin sugbenre

  #122 opened 3 years ago by JorgeRuizDev
  0

• Implement an OVO Architecture (32 CNNs)

  #133 opened 3 years ago by JorgeRuizDev
  0

• Extract Similarity Features

  #134 opened 3 years ago by JorgeRuizDev
  0

• Implement Python Genre + Subgenres Inference Engine based on ONNX

  #116 opened 3 years ago by JorgeRuizDev
  0

• Explore the signal extracted features with knime

  #135 opened 3 years ago by JorgeRuizDev
  0

• Add a mood pie chart in the view statistics

  #137 opened 3 years ago by JorgeRuizDev
  0

• Allow batching requests for improved performance

  #131 opened 3 years ago by JorgeRuizDev
  0

• Cache Ludwig Analysis & Recommendations

  #144 opened 3 years ago by JorgeRuizDev
  0

• Connect Bowie and Ludwig backends

  #128 opened 3 years ago by JorgeRuizDev
  0

• Secure the Ludwig-mir-backend with JWT Token Bearer + Secret Token shared between Bowie and Ludwig

  #125 opened 3 years ago by JorgeRuizDev
  0

• Music file upload endpoint + component + page

  #143 opened 3 years ago by JorgeRuizDev
  0

• Integrate Recommendation System with the frontend

  #140 opened 3 years ago by JorgeRuizDev
  0

• Integrate Mood / Subgenres with the frontend

  #139 opened 3 years ago by JorgeRuizDev
  0

• Quantize the models to reduce the memory footprint

  #138 opened 3 years ago by JorgeRuizDev
  0

• Internationalize SpotMyFM to Spanish

  #130 opened 3 years ago by JorgeRuizDev
  0

• Dockerize NextJS Package

  #126 opened 3 years ago by JorgeRuizDev
  0

• Build the MIR backend with FastAPI

  #121 opened 3 years ago by JorgeRuizDev
  0

• Try training an adaboost of cnn

  #123 opened 3 years ago by JorgeRuizDev
  0

• Dockerize and Publish the MIR Backend to Google Cloud

  #124 opened 3 years ago by JorgeRuizDev
  0

• Implement a CNN + SVM for genre classification

  #132 opened 3 years ago by JorgeRuizDev
  0

• Train a mood classifier with the OVA

  #120 opened 3 years ago by JorgeRuizDev
  0

• Design Python Inference Engine

  #115 opened 3 years ago by JorgeRuizDev
  0

• Dataset-Tools: Node Script that replaces/removes tracks without a preview from a playlist

  #105 opened 3 years ago by JorgeRuizDev
  0

• Subgenre Dataset Data Modeling

  #108 opened 3 years ago by JorgeRuizDev
  0

• Datset-Tools: Python Script that preprocess all the tracks/splits and saves them

  #109 opened 3 years ago by JorgeRuizDev
  0

• Dataset-Tools: Discogs Acoustic Brainz Parser

  #110 opened 3 years ago by JorgeRuizDev
  0

• Explore gtzan_features.csv with Knime

  #103 opened 3 years ago by JorgeRuizDev
  0

• Dataset-Tools Python: Download each preview and export the MFCCs as numpy files

  #111 opened 3 years ago by JorgeRuizDev
  0

• Research PCA, K-Means and DBScan techniques

  #104 opened 3 years ago by JorgeRuizDev
  0

• Dataset-Tools: Node Script that uploads each playlist data to DynamoDB as a subgenre

  #106 opened 3 years ago by JorgeRuizDev
  0

• Dataset-Tools: Node script that dowloads a JSON file with the different labels an all saved tracks from the Dynamo Dataset

  #107 opened 3 years ago by JorgeRuizDev
  0

• Create Dataset and push to Kaggle

  #114 opened 3 years ago by JorgeRuizDev
  0

• Try to improve the CNN generalization for Ludwig Dataset

  #117 opened 3 years ago by JorgeRuizDev
  0

• Replace librosa.load() with pydub to improve the audio reading performance.

  #102 opened 3 years ago by JorgeRuizDev
  1