Instructions to use MU-NLPC/whisper-tiny-audio-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MU-NLPC/whisper-tiny-audio-captioning with Transformers:
# Load model directly from transformers import AutoProcessor, WhisperForAudioCaptioning processor = AutoProcessor.from_pretrained("MU-NLPC/whisper-tiny-audio-captioning") model = WhisperForAudioCaptioning.from_pretrained("MU-NLPC/whisper-tiny-audio-captioning") - Notebooks
- Google Colab
- Kaggle
Finetune on our dataset
#5
by Megatron17 - opened
Is there any tutorial that exists that shows how to finetune this model on our dataset
Hi @Megatron17 ,
You can train/finetune a model using this repository: https://github.com/prompteus/audio-captioning/
This repo was used to produce the models here on HuggingFace.
The readme should get you started.