metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- make_dataset
model-index:
- name: wav2vec2-large-xls-r-300m-korean-g
results: []
wav2vec2-large-xls-r-300m-korean-g
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the make_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 245.9002
- Cer: 0.8609
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 19.5527 | 500.0 | 500 | 105.0973 | 0.9536 |
| 0.486 | 1000.0 | 1000 | 245.9002 | 0.8609 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2