m-ctc-t-german
This model is a fine-tuned version of speechbrain/m-ctc-t-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 14.0387
- Wer: 1.0000
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: 448
- eval_batch_size: 448
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 896
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.1883 | 1.0 | 511 | 3.5192 | 1.0 |
| 3.1097 | 2.0 | 1022 | 11.0713 | 1.0000 |
| 3.0541 | 3.0 | 1533 | 14.0387 | 1.0000 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0
- Datasets 2.4.0
- Tokenizers 0.12.1