basic_train_basic_test 1000 similar params: per_device_train_batch_size=32, # bylo 16 a pod tim 1 gradient_accumulation_steps=2, warmup_steps=300, max_steps=3000
This model is a fine-tuned version of openai/whisper-small on the xbilek25/train_set_1st_1000_de_en_de dataset. It achieves the following results on the evaluation set:
- Loss: 0.5705
- Wer: 24.4182
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 800
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0049 | 6.03 | 400 | 0.5474 | 24.5194 |
| 0.0022 | 12.05 | 800 | 0.5705 | 24.4182 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 85
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for xbilek25/whisper-small-train-v3.2
Base model
openai/whisper-smallDataset used to train xbilek25/whisper-small-train-v3.2
Evaluation results
- Wer on xbilek25/train_set_1st_1000_de_en_deself-reported24.418