Whisper Medium Libyan

--- library_name: transformers language: - ar license: apache-2.0 base_model: openai/whisper-medium tags: - generated_from_trainer metrics: - wer model-index: - name: "Whisper medium \u2014 Libyan Arabic Dialect" results: [] --- # Whisper medium — Libyan Arabic Dialect This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Custom Libyan Arabic podcast — 258 manually transcribed clips dataset. It achieves the following results on the evaluation set: - Loss: 0.7577 - Wer: 34.7790 ## 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: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - 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: linear - lr_scheduler_warmup_steps: 25 - training_steps: 500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-------:|:----:|:---------------:|:-------:| | 0.1566 | 6.6897 | 100 | 0.5647 | 34.1952 | | 0.0242 | 13.3448 | 200 | 0.6333 | 35.2794 | | 0.0120 | 20.0 | 300 | 0.7126 | 35.7798 | | 0.0018 | 26.6897 | 400 | 0.7480 | 35.0292 | | 0.0014 | 33.3448 | 500 | 0.7577 | 34.7790 | ### Framework versions - Transformers 5.12.0 - Pytorch 2.11.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2