datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
lj_speech_with_spectogram
Explanation
A small experiment insipred by the Mistral playing DOOM experiment from the Mistral Hackathon
How it works?
Audio -> Waveform Visualization -> Waveform ASCII Art -> Finetune Mistral on ASCII Art to predict text from ASCII Art
Quick video explanation
Example Waveform
Example ASCII Art… See the full description on the dataset page: https://huggingface.co/datasets/0-hero/lj_speech_with_spectogram.audio-samples-fixedheroes3cu