metadata
library_name: transformers
language:
- pl
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- classla/ParlaSpeech-PL
metrics:
- wer
model-index:
- name: Whisper Small Pl - Jan Stusio
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ParlaSpeech Pl
type: classla/ParlaSpeech-PL
args: 'config: pl, split: test'
metrics:
- name: Wer
type: wer
value: 69.04761904761905
Whisper Small Pl - Jan Stusio
This model is a fine-tuned version of openai/whisper-small on the ParlaSpeech Pl dataset. It achieves the following results on the evaluation set:
- Loss: 0.4903
- Wer: 69.0476
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: 1
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adamw_torch_fused 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: 10
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3228 | 6.32 | 25 | 0.4705 | 70.8333 |
| 0.0071 | 12.64 | 50 | 0.4903 | 69.0476 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0
- Datasets 4.3.0
- Tokenizers 0.22.1