Task
Automatic Speech Recognition
W
kresnik/wav2vec2-large-xlsr-korean
Automatic Speech Recognition·kresnik· 853.8K· 56
transformers
apache-2.0
316.7M params
dataset:kresnik/zeroth_koreanlicense:apache-2.0
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor from datasets import loaddataset import soundfile as sf import torch from jiwer import wer
# pull & run locally
pip install mlforge-sdk && mlforge pull kresnik/wav2vec2-large-xlsr-korean
pip install mlforge-sdk && mlforge pull kresnik/wav2vec2-large-xlsr-korean
Model details
Provider
kresnik
Framework
transformers
Parameters
316.7M
Size
8.2 GB
License
apache-2.0
Downloads
853.8K
Likes
56
Updated
2023-07-03
About kresnik/wav2vec2-large-xlsr-korean
Evaluation on Zeroth-Korean ASR corpus Google colab notebook(Korean) Expected WER: 4.74% Expected CER: 1.78%