Whisper Small Pashto

--- library_name: transformers license: apache-2.0 base_model: ihanif/whisper_small_ps_augmented tags: - generated_from_trainer metrics: - wer model-index: - name: whisper-small-pashto results: [] --- # whisper-small-pashto This model is a fine-tuned version of [ihanif/whisper_small_ps_augmented](https://huggingface.co/ihanif/whisper_small_ps_augmented) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6467 - Wer: 36.4146 ## 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: 3e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 1500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 0.322 | 0.6349 | 100 | 0.4170 | 37.4790 | | 0.2311 | 1.2698 | 200 | 0.4376 | 38.7302 | | 0.2311 | 1.9048 | 300 | 0.4682 | 39.4958 | | 0.1132 | 2.5397 | 400 | 0.5162 | 38.4127 | | 0.0577 | 3.1746 | 500 | 0.5453 | 38.9729 | | 0.0596 | 3.8095 | 600 | 0.5689 | 38.7675 | | 0.0301 | 4.4444 | 700 | 0.6020 | 37.9458 | | 0.0212 | 5.0794 | 800 | 0.6143 | 37.3856 | | 0.011 | 5.7143 | 900 | 0.6127 | 36.9374 | | 0.0054 | 6.3492 | 1000 | 0.6380 | 36.5640 | | 0.005 | 6.9841 | 1100 | 0.6339 | 36.5453 | | 0.0019 | 7.6190 | 1200 | 0.6462 | 36.2652 | | 0.0014 | 8.2540 | 1300 | 0.6431 | 36.4706 | | 0.0012 | 8.8889 | 1400 | 0.6463 | 36.3772 | | 0.0012 | 9.5238 | 1500 | 0.6467 | 36.4146 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu118 - Datasets 4.8.5 - Tokenizers 0.19.1