<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-base-vi-vlsp2020-demo
This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vi-vlsp2020 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2509
- Wer: 0.1280
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
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8445 | 1.0 | 787 | 0.3264 | 0.1494 |
| 0.5248 | 2.0 | 1574 | 0.2784 | 0.1365 |
| 0.445 | 3.0 | 2361 | 0.2509 | 0.1280 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
