<!-- 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. -->
Sl ASR Model Small
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4800
- Wer: 2.4741
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: 1.25e-05
- train_batch_size: 32
- 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: 400
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0083 | 7.63 | 1000 | 0.4456 | 2.5962 |
| 0.0007 | 15.27 | 2000 | 0.4800 | 2.4741 |
| 0.0003 | 22.9 | 3000 | 0.4974 | 3.5620 |
| 0.0002 | 30.53 | 4000 | 0.5041 | 3.7114 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0
