Whisper small audio captioning

This model is a finetuned whisper-small model with 1M audio caption samples from the dataset mitermix/audiosnippets and 500K samples of audio emotion dataset.

Downloads last month
9
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Collection including cahya/whisper-small-emotion-v1.0