---
license: apache-2.0
datasets:
- mitermix/audiosnippets
language:
- en
metrics:
- sacrebleu
- meteor
base_model:
- openai/whisper-tiny
---

# whisper-tiny-audio-captioning-v2.0

This model is a finetuned whisper-tiny model with 1M audio samples from the dataset [mitermix/audiosnippets](https://huggingface.co./datasets/laion/mitermix/audiosnippets/)