Downloads · 30 days
61
14% of all-time downloads
wav2vec2_japanese
kwmr/wav2vec2_japanese
wav2vec2_japanese is a automatic speech recognition model from kwmr. Use it when you need speech turned into text. It is set up for transformers.
facebook/wav2vec2-large-xlsr-53を日本語用にFine Tuningしたモデル
All-time downloads
451
Public
Repo size
3.8 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- Jul 7, 2022
- Updated
- Jul 7, 2022
- SHA
- f7b020bb
Model card
From the Hugging Face model README
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
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")
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Jul 7, 2022
- Updated
- Jul 7, 2022