[Feature request] Add evaluator for audio classification #379
Comments
|
I would like to work on this feature, if it's not already being implemented. |
|
I don't think so, so feel free to go ahead :) |
unna97
pushed a commit
to unna97/evaluate
that referenced
this issue
Mar 20, 2023
…gface#405) * audio classification evaluator + docs * fix styling issue * [Docs] fixed a typo in bertscore readme (huggingface#386) fixed typo in berscore readme * Add max_length kwarg to docstring of Perplexity measurement (huggingface#411) Added max_length kwarg to docstring of Perplexity measurement * adding support raw audio input audio classification evaluator --------- Co-authored-by: Hazrul Akmal <hazrulakmal121@gmail.com> Co-authored-by: Kalyan Dutia <kalyan.dutia@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
We have a few hundred audio classification models from
transformerson the Hub and it would be nice if one could easily evaluate them for accuracy, F1 score etc with an evaluator.The pipeline in question is
audio-classificationand the relevant docs are here.A good model/dataset pair to test is this one for keyword spotting (ks):
superb/wav2vec2-base-superb-ks: https://huggingface.co/superb/wav2vec2-base-superb-ksksconfig ofsuperb: https://huggingface.co/datasets/superbTogether with #324, this evaluator would bring coverage to all audio
transformersmodels on the Hub 🔥The text was updated successfully, but these errors were encountered: