--- library_name: transformers language: - sq license: apache-2.0 base_model: openai/whisper-medium tags: - hf-asr-leaderboard - generated_from_trainer datasets: - Kaggle_Albanian metrics: - wer model-index: - name: Whisper Medium Kaggle results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Kaggle Albanian type: Kaggle_Albanian args: 'config: sq, split: test' metrics: - name: Wer type: wer value: 13.208955223880597 --- # Whisper Medium Kaggle This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Kaggle Albanian dataset. It achieves the following results on the evaluation set: - Loss: 0.2751 - Wer: 13.2090 ## 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: 8 - eval_batch_size: 4 - seed: 42 - optimizer: Use OptimizerNames.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: 500 - training_steps: 2000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 0.0536 | 3.8911 | 1000 | 0.2503 | 13.0100 | | 0.0048 | 7.7821 | 2000 | 0.2751 | 13.2090 | ### Framework versions - Transformers 4.49.0.dev0 - Pytorch 2.5.1+cu124 - Datasets 3.3.0 - Tokenizers 0.21.0