t5-asr-CV16
This model is a fine-tuned version of google/umt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6678
- Wer: 0.7639
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 4096
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.8105 | 1.9694 | 48 | 0.7812 | 0.8528 |
| 1.6752 | 3.9694 | 96 | 0.7174 | 0.8285 |
| 1.6146 | 5.9694 | 144 | 0.7357 | 0.8215 |
| 1.3847 | 7.9694 | 192 | 0.6796 | 0.8172 |
| 1.2792 | 9.9694 | 240 | 0.6601 | 0.7841 |
| 1.2129 | 11.9694 | 288 | 0.6540 | 0.7764 |
| 1.279 | 13.9694 | 336 | 0.6792 | 0.7837 |
| 1.1706 | 15.9694 | 384 | 0.6695 | 0.7888 |
| 1.0348 | 17.9694 | 432 | 0.6931 | 0.7948 |
| 0.9335 | 19.9694 | 480 | 0.6678 | 0.7639 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 2.17.1
- Tokenizers 0.21.0
- Downloads last month
- 45
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for urarik/t5-asr-CV16
Base model
google/umt5-small