metadata
license: mit
language:
- en
- fr
- es
- pt
- de
base_model:
- coml/BabyHuBERT
pipeline_tag: automatic-speech-recognition
BabAR is an end-to-end algorithm for phoneme recognition from child-centered long-form audio recordings (although it can be applied to any recordings). This huggingface repository is used only to store the model's weights. Everything you need to run BabAR can be found at https://github.com/MarvinLvn/BabAR