cvwav2vec2-large-xlsr-53-common-voice-sw
This model is a fine-tuned version of Professor/cvwav2vec2-large-xlsr-53-common-voice-sw on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1056
- Wer: 0.1039
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1161 | 0.22 | 1000 | 0.1324 | 0.1295 |
| 0.1241 | 0.43 | 2000 | 0.1306 | 0.1289 |
| 0.1147 | 0.65 | 3000 | 0.1152 | 0.1166 |
| 0.1236 | 0.87 | 4000 | 0.1056 | 0.1039 |
Framework versions
- Transformers 4.18.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.12.1