<!-- 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-xls-r-300m-kor-11385-2
This model is a fine-tuned version of teddy322/wav2vec2-large-xls-r-300m-kor-11385 on the zeroth_korean_asr dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2059
- eval_wer: 0.1471
- eval_runtime: 136.7247
- eval_samples_per_second: 3.342
- eval_steps_per_second: 0.424
- epoch: 6.47
- step: 4400
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 12
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3