<!-- 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_finetuned_on_grid
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3388
- Wer: 0.8007
- Cer: 0.4451
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: 0.001
- train_batch_size: 16
- 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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
---|---|---|---|---|---|
7.2521 | 3.33 | 500 | 0.3804 | 0.9541 | 0.2804 |
0.7856 | 6.67 | 1000 | 0.3611 | 0.7816 | 0.3855 |
0.7404 | 10.0 | 1500 | 0.3604 | 0.7314 | 0.3776 |
0.6163 | 13.33 | 2000 | 0.3458 | 0.7854 | 0.4055 |
0.5907 | 16.67 | 2500 | 0.3354 | 0.8375 | 0.4511 |
0.6053 | 20.0 | 3000 | 0.3388 | 0.8007 | 0.4451 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3