Audio Captioning datasets for PyTorch.

Using pretrained encoder and language models to generate captions from multimedia inputs.

Python code for handling the Clotho dataset.

Song Describer is a data collection platform for annotating music with textual descriptions.

Code base for WaveTransformer: A novel architecture for automated audio captioning

Metrics for evaluating Automated Audio Captioning systems, designed for PyTorch.

Audio captioning baseline system for DCASE 2020 challenge.

2nd place solution for 2020 DCASE challenge task 6 audio captioning. http://dcase.community/challenge2020/task-automatic-audio-captioning-results#wuyusong2020_t6

Fluency ENhanced Sentence-bert Evaluation (FENSE), metric for audio caption evaluation. And Benchmark dataset AudioCaps-Eval, Clotho-Eval.

[NeurIPS 2023 - ML for Audio Workshop (Oral)] Zero-shot audio captioning with audio-language model guidance and audio context keywords

CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding

Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning

Code for the paper: MACE: Leveraging Audio for Evaluating Audio Captioning Systems

DCASE2024 Challenge Task 6 baseline system (Automated Audio Captioning)

6-th task solution of DCASE2020

PyTorch dataloader for Clotho dataset.

Code for using with the Clotho dataset

This reporsitory code form Weakly Supervised Automaed Audio Captioning via Text Only Training

IRIT-UPS DCASE 2021 AUDIO CAPTIONING SYSTEM