Instructions to use espnet/DCASE23.AudioCaptioning.FineTuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/DCASE23.AudioCaptioning.FineTuned with ESPnet:
unknown model type (must be text-to-speech or automatic-speech-recognition)
- Notebooks
- Google Colab
- Kaggle
metadata
tags:
- espnet
- audio
- audio_captioning
language: en
datasets:
- clotho_v2
- slseanwu/clotho-chatgpt-mixup-50K
- audiocaps
license: cc-by-4.0