metadata
library_name: transformers
license: cc-by-sa-4.0
base_model: airesearch/wav2vec2-large-xlsr-53-th
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec-th-test
results: []
wav2vec-th-test
This model is a fine-tuned version of airesearch/wav2vec2-large-xlsr-53-th on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4948
- Wer: 0.7257
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: 32
- 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: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
4.0857 | 40.0 | 1000 | 1.8510 | 0.7806 |
0.6534 | 80.0 | 2000 | 2.4948 | 0.7257 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1