Name: Florian Schmid
Type: User
Company: Johannes Kepler University
Bio: University Assistant @CPJKU Linz
Working on Audio Classification, Audio Tagging, Acoustic Scene Classification, Low-Complexity Models
Twitter: Florian04130962
Location: Linz
Florian Schmid's Projects
This repository contains the code of the CP JKU submission to DCASE23 Task 1 "Low-complexity Acoustic Scene Classification"
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.
Evaluate EfficientAT models on the Holistic Evaluation of Audio Representations Benchmark.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Config files for my GitHub profile.
Submission to leaderboard for HEAR benchmark
Efficient Training of Audio Transformers with Patchout
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities