Wav2Vec2.0 XLSR-53 large model の日本語 Fine Tuning モデル

facebook/wav2vec2-large-xlsr-53を日本語用にFine Tuningしたモデル

使用データセット

• Common Voice

使い方

from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
from datasets import load_dataset
import torch
 
# load model and processor
processor = Wav2Vec2Processor.from_pretrained("kwmr/wav2vec2_japanese")
model = Wav2Vec2ForCTC.from_pretrained("kwmr/wav2vec2_japanese")