hyyoka's picture
Add model card
066d5b1
|
raw
history blame
600 Bytes
metadata
language: kr
datasets:
  - aihub 자유대화 음성(노인남녀)
tags:
  - automatic-speech-recognition
license: apache-2.0

wav2vec2-xlsr-korean-senior

Futher fine-tuned fleek/wav2vec-large-xlsr-korean using the AIhub 자유대화 음성(노인남녀).

  • Total train data size: 808,642
  • Total vaild data size: 159,970

When using this model, make sure that your speech input is sampled at 16kHz.

The script used for training can be found here: https://github.com/hyyoka/wav2vec2-korean-senior