Whisper Small Pl - Fardin Chowdhury
This model is a fine-tuned version of openai/whisper-small on the Multilingual Librispeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.1595
- Wer Ortho: 10.8782
- Wer: 10.9017
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.5640 | 0.6386 | 500 | 0.1595 | 10.8782 | 10.9017 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2
- Downloads last month
- 2
Model tree for 2rj0/whisper-small-pl
Base model
openai/whisper-smallDataset used to train 2rj0/whisper-small-pl
Evaluation results
- Wer on Multilingual Librispeechself-reported10.902