model trenovan na de setu, nastaveni jazyka de
This model is a fine-tuned version of openai/whisper-medium on the xbilek25/train_set_1st_1000_de_en_de dataset. It achieves the following results on the evaluation set:
- Loss: 0.1983
- Wer: 48.1320
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: 1
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0468 | 1.25 | 1000 | 0.1860 | 27.8659 |
| 0.0034 | 3.25 | 2000 | 0.1983 | 48.1320 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for xbilek25/w-m-lang_de-set_de
Base model
openai/whisper-mediumDataset used to train xbilek25/w-m-lang_de-set_de
Evaluation results
- Wer on xbilek25/train_set_1st_1000_de_en_deself-reported48.132