<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-large-xlsr-53-korean-samsung-60k
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the NIA13 ASIA dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Training Data
- Data Name: NIA13 ASIA
- Num. of Samples: 9,634
- Audio Length: 9H 42M
Evaluation Data
- Data Name: NIA13 ASIA
- Num. of Samples: 3,707
- Audio Length: 3H 37M
Test Data
- Data Name: NIA13 ASIA (Same as the Evaluation Data)
- Num. of Samples: 3,707
- Audio Length: 3H 37M
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
Training results
- Validation Phone Error Rate: 19.90%
- Test Phone Error Rate: 19.90%
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1
- Datasets 2.4.0
- Tokenizers 0.12.1