metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-large-asr-th
results: []
wav2vec2-large-asr-th
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: 3.7473
- Cer: 0.9999
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: 0.0005
- train_batch_size: 16
- 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: 250
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 4.2296 | 0.56 | 100 | 4.0607 | 0.9999 |
| 3.6029 | 1.13 | 200 | 3.9200 | 0.9999 |
| 3.6003 | 1.69 | 300 | 3.7882 | 0.9999 |
| 3.6346 | 2.26 | 400 | 3.7473 | 0.9999 |
| 3.6041 | 2.82 | 500 | 3.9651 | 0.9999 |
| 3.5491 | 3.39 | 600 | 3.9053 | 0.9999 |
| 3.568 | 3.95 | 700 | 3.7021 | 0.9999 |
| 3.5773 | 4.52 | 800 | 3.6694 | 0.9999 |
| 3.5367 | 5.08 | 900 | 3.6426 | 0.9999 |
| 3.5112 | 5.65 | 1000 | 3.6260 | 0.9999 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2