<!-- 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-large-xls-r-300m-slowakisch-home4
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5308
- Wer: 0.4327
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
7.1691 | 2.44 | 400 | 3.1326 | 1.0 |
0.9673 | 4.88 | 800 | 0.6624 | 0.6227 |
0.3 | 7.32 | 1200 | 0.5933 | 0.4976 |
0.1571 | 9.76 | 1600 | 0.5308 | 0.4327 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3