metadata
license: apache-2.0
base_model: zainulhakim/240615-wav2vec2-ASR-English
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: 240624-wav2vec2-ASR-English
results: []
240624-wav2vec2-ASR-English
This model is a fine-tuned version of zainulhakim/240615-wav2vec2-ASR-English on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8851
- Wer: 0.5584
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 5.0 | 100 | 2.6338 | 1.0 |
| No log | 10.0 | 200 | 0.8716 | 0.9221 |
| No log | 15.0 | 300 | 0.8093 | 0.6753 |
| No log | 20.0 | 400 | 0.7692 | 0.6494 |
| 1.766 | 25.0 | 500 | 1.0466 | 0.5714 |
| 1.766 | 30.0 | 600 | 0.8851 | 0.5584 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1