metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-asr-th-2
results: []
wav2vec2-large-asr-th-2
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3300
- Wer: 0.4924
- Cer: 0.1398
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 600
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.2666 | 0.24 | 1000 | 0.7343 | 0.6934 | 0.2410 |
| 0.9305 | 0.47 | 2000 | 0.4504 | 0.6006 | 0.1764 |
| 0.8241 | 0.71 | 3000 | 0.3653 | 0.5278 | 0.1547 |
| 0.7788 | 0.95 | 4000 | 0.3300 | 0.4924 | 0.1398 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2