cahya
/

whisper-tiny-audio-captioning-v1.5

Model card Files Files and versions Community

whisper-tiny-audio-captioning-v1.5

This model is a finetuned whisper-tiny model with 300k audio samples from the dataset laion/laion-audio-preview

Downloads last month: 21

Safetensors

Model size

37.8M params

Tensor type

F32

·

Inference API

Unable to determine this model's library. Check the docs .

Model tree for cahya/whisper-tiny-audio-captioning-v1.5

Base model

openai/whisper-tiny

Finetuned

(1283)

this model

Dataset used to train cahya/whisper-tiny-audio-captioning-v1.5