Returns common English accent given a voice audio sample.

See https://www.kaggle.com/code/dima806/common-voice-accent-classification for more details.

Classification report:

              precision    recall  f1-score   support

          us     0.3956    0.0150    0.0290      4788
     england     0.5255    0.9121    0.6668     18082
      indian     0.5883    0.4586    0.5154      5656
   australia     0.4962    0.0381    0.0707      5124
      canada     0.3714    0.1760    0.2389      5169

    accuracy                         0.5220     38819
   macro avg     0.4754    0.3200    0.3042     38819
weighted avg     0.4942    0.5220    0.4304     38819

Downloads last month: 310

Safetensors

Model size

94.6M params

Tensor type

F32

Inference Examples

Audio Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for dima806/english_accents_classification

Base model

facebook/wav2vec2-base-960h

Finetuned

(121)

this model