metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- zeroth_korean
metrics:
- wer
model-index:
- name: wav2vec2-large-xlrs-korean-v4
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: zeroth_korean
type: zeroth_korean
config: clean
split: None
args: clean
metrics:
- name: Wer
type: wer
value: 0.37644932992019275
wav2vec2-large-xlrs-korean-v4
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the zeroth_korean dataset. It achieves the following results on the evaluation set:
- Loss: 0.1717
- Wer: 0.3764
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.1045 | 5.7471 | 500 | 0.7609 | 0.8794 |
0.3215 | 11.4943 | 1000 | 0.2375 | 0.4843 |
0.1928 | 17.2414 | 1500 | 0.1717 | 0.3764 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1