wav2vec2-E30_speed2.1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.2722
- Cer: 88.7864
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: 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: 50
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 47.3913 | 0.2577 | 200 | 7.0350 | 100.0 |
| 8.4649 | 0.5155 | 400 | 5.0178 | 93.8205 |
| 6.1517 | 0.7732 | 600 | 4.5573 | 92.2580 |
| 5.5969 | 1.0309 | 800 | 4.4801 | 93.7441 |
| 5.3362 | 1.2887 | 1000 | 4.4471 | 93.7852 |
| 5.212 | 1.5464 | 1200 | 4.4210 | 92.8806 |
| 5.7549 | 1.8041 | 1400 | 4.3906 | 93.1920 |
| 5.4739 | 2.0619 | 1600 | 4.3616 | 92.3637 |
| 5.6889 | 2.3196 | 1800 | 4.3293 | 89.1095 |
| 4.7739 | 2.5773 | 2000 | 4.2981 | 87.7115 |
| 4.3768 | 2.8351 | 2200 | 4.2722 | 88.7864 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.20.1
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Gummybear05/wav2vec2-E30_speed2.1
Base model
facebook/wav2vec2-xls-r-300m