README.md

metadata

language:
  - multilingual
  - en
  - id
  - ja
  - ko
  - th
  - vi
  - zh
tags:
  - LID
  - spoken language recognition
license: apache-2.0
datasets:
  - VoxLingua107
metrics:
  - ER
inference: false

Spoken Language Identification Model

Model description

The model can classify a speech utterance according to the language spoken. It covers following different languages ( English, Indonesian, Japanese, Korean, Thai, Vietnamese, Mandarin Chinese).