---
license: apache-2.0
datasets:
- laion/laion-audio-preview
language:
- en
metrics:
- sacrebleu
- meteor
base_model:
- openai/whisper-tiny
---

# whisper-tiny-audio-captioning-v1.0

This model is a finetuned whisper-tiny model with 100k audio samples from the dataset [laion/laion-audio-preview](https://huggingface.co/datasets/laion/laion-audio-preview/)