wav2vec2-large-xlsr-sw_ndizi_782_NF4-April-1
This model is a fine-tuned version of smutuvi/wav2vec2-large-xlsr-sw-common-voice-16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1139
- Wer: 0.9993
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.1072 | 1.0 | 135 | 3.4546 | 0.9993 |
| 2.88 | 2.0 | 270 | 3.1342 | 0.9986 |
| 2.9526 | 3.0 | 405 | 3.2622 | 1.0 |
| 2.8646 | 4.0 | 540 | 3.0074 | 1.0 |
| 2.8826 | 5.0 | 675 | 3.0303 | 0.9993 |
| 2.8805 | 6.0 | 810 | 3.4972 | 1.0028 |
| 2.8354 | 7.0 | 945 | 3.3143 | 1.0036 |
| 2.8927 | 8.0 | 1080 | 3.0944 | 1.0 |
| 2.8531 | 9.0 | 1215 | 3.2952 | 1.0178 |
| 2.8569 | 10.0 | 1350 | 3.1139 | 0.9993 |
Framework versions
- PEFT 0.9.0
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.18.0
- Tokenizers 0.15.1