metadata
library_name: transformers
license: mit
base_model: dawid511/speecht5_finetuned_librispeech_polish_epo6_batch2_gas4
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_librispeech_polish_epo6_batch4_gas2
results: []
speecht5_finetuned_librispeech_polish_epo6_batch4_gas2
This model is a fine-tuned version of dawid511/speecht5_finetuned_librispeech_polish_epo6_batch2_gas4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3653
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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_steps: 100
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7593 | 0.5115 | 100 | 0.3747 |
| 0.786 | 1.0205 | 200 | 0.3787 |
| 0.7781 | 1.5320 | 300 | 0.3732 |
| 0.767 | 2.0409 | 400 | 0.3830 |
| 0.7654 | 2.5524 | 500 | 0.3753 |
| 0.7471 | 3.0614 | 600 | 0.3697 |
| 0.7531 | 3.5729 | 700 | 0.3672 |
| 0.7365 | 4.0818 | 800 | 0.3716 |
| 0.7385 | 4.5934 | 900 | 0.3674 |
| 0.7218 | 5.1023 | 1000 | 0.3692 |
| 0.7326 | 5.6138 | 1100 | 0.3653 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0