|
--- |
|
language: |
|
- multilingual |
|
license: apache-2.0 |
|
tags: |
|
- voice |
|
- classification |
|
- vocalization |
|
- speech |
|
- audio |
|
datasets: |
|
- NonverbalVocalization |
|
widget: |
|
- src: >- |
|
https://huggingface.co/padmalcom/wav2vec2-large-nonverbalvocalization-classification/resolve/main/test.wav |
|
example_title: Sample 1 |
|
pipeline_tag: audio-classification |
|
metrics: |
|
- accuracy |
|
--- |
|
This language indendent wav2vec2 classification model is based on [this dataset](https://github.com/deeplyinc/Nonverbal-Vocalization-Dataset). |
|
|
|
Sound classes are: |
|
- teeth-chattering |
|
- teeth-grinding |
|
- tongue-clicking |
|
- nose-blowing |
|
- coughing |
|
- yawning |
|
- throat clearing |
|
- sighing |
|
- lip-popping |
|
- lip-smacking |
|
- panting |
|
- crying |
|
- laughing |
|
- sneezing |
|
- moaning |
|
- screaming |
|
|
|
*inference.py* shows, how the model can be used. |
