metadata
base_model: facebook/wav2vec2-base
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-large-xls-r-vi-colab
results: []
wav2vec2-large-xls-r-vi-colab
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5540
- Wer: 1.0
- Cer: 1.0
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: 8
- 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 | Cer |
|---|---|---|---|---|---|
| 9.6481 | 2.3864 | 315 | 4.4676 | 1.0 | 1.0 |
| 3.8703 | 4.7727 | 630 | 4.4033 | 1.0 | 1.0 |
| 3.4149 | 7.1591 | 945 | 4.7546 | 1.0 | 1.0 |
| 3.4323 | 9.5455 | 1260 | 4.2532 | 1.0 | 1.0 |
| 3.4127 | 11.9318 | 1575 | 4.6692 | 1.0 | 1.0 |
| 3.4185 | 14.3182 | 1890 | 4.3411 | 1.0 | 1.0 |
| 3.4112 | 16.7045 | 2205 | 4.5614 | 1.0 | 1.0 |
| 3.4074 | 19.0909 | 2520 | 4.3545 | 1.0 | 1.0 |
| 3.4073 | 21.4773 | 2835 | 4.4929 | 1.0 | 1.0 |
| 3.4004 | 23.8636 | 3150 | 4.6089 | 1.0 | 1.0 |
| 3.4099 | 26.25 | 3465 | 4.5189 | 1.0 | 1.0 |
| 3.3972 | 28.6364 | 3780 | 4.5540 | 1.0 | 1.0 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1