Whisper Small Pashto

--- base_model: ihanif/whisper_small_ps_augmented library_name: transformers license: apache-2.0 metrics: - wer tags: - generated_from_trainer model-index: - name: whisper-small-pashto results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 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: 0.3364 - Wer: 32.6050 ## 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: 5e-06 - 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: linear - lr_scheduler_warmup_steps: 600 - training_steps: 21854 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 1.321 | 0.0137 | 100 | 0.2794 | 28.2726 | | 1.1509 | 0.0275 | 200 | 0.3045 | 29.4678 | | 1.0585 | 0.0412 | 300 | 0.3154 | 30.4388 | | 1.0012 | 0.0549 | 400 | 0.3218 | 30.4575 | | 0.9466 | 0.0686 | 500 | 0.3329 | 32.4370 | | 0.9275 | 0.0824 | 600 | 0.3364 | 32.6050 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu118 - Datasets 2.19.0 - Tokenizers 0.19.1

--- 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: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 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: 0.3409 - Wer: 31.7087 ## 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: 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: linear - lr_scheduler_warmup_steps: 200 - training_steps: 1701 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 0.5189 | 0.5875 | 250 | 0.3536 | 34.3604 | | 0.3469 | 1.1751 | 500 | 0.3535 | 33.3147 | | 0.3594 | 1.7626 | 750 | 0.3417 | 33.4267 | | 0.2385 | 2.3502 | 1000 | 0.3488 | 32.6424 | | 0.2297 | 2.9377 | 1250 | 0.3380 | 31.9514 | | 0.1968 | 3.5253 | 1500 | 0.3409 | 31.7087 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu118 - Datasets 2.19.0 - Tokenizers 0.19.1

--- 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: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 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