Jem Whisper Yi 2026 06 11

--- library_name: transformers license: apache-2.0 base_model: ivrit-ai/yi-whisper-large-v3 tags: - generated_from_trainer metrics: - wer model-index: - name: jem-whisper-yi-2026-06-11 results: [] --- # jem-whisper-yi-2026-06-11 This model is a fine-tuned version of [ivrit-ai/yi-whisper-large-v3](https://huggingface.co/ivrit-ai/yi-whisper-large-v3) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1419 - Wer Ortho: 0.2816 - Wer: 0.2300 ## 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: 4 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - 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: constant_with_warmup - lr_scheduler_warmup_ratio: 0.1 - lr_scheduler_warmup_steps: 100 - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:------:|:----:|:---------------:|:---------:|:------:| | 0.4957 | 0.3040 | 100 | 0.4404 | 0.5407 | 0.5407 | | 0.3999 | 0.6079 | 200 | 0.3435 | 0.4967 | 0.4329 | | 0.3708 | 0.9119 | 300 | 0.3162 | 0.6885 | 0.3544 | | 0.2879 | 1.2158 | 400 | 0.2776 | 0.4228 | 0.4322 | | 0.2794 | 1.5198 | 500 | 0.2567 | 0.3729 | 0.3565 | | 0.2727 | 1.8237 | 600 | 0.2538 | 0.4045 | 0.4051 | | 0.2077 | 2.1277 | 700 | 0.2207 | 0.6188 | 0.2363 | | 0.2134 | 2.4316 | 800 | 0.2138 | 0.3439 | 0.3329 | | 0.2154 | 2.7356 | 900 | 0.1979 | 0.3040 | 0.2613 | | 0.1586 | 3.0395 | 1000 | 0.1768 | 0.3189 | 0.2613 | | 0.1603 | 3.3435 | 1100 | 0.1588 | 0.2658 | 0.2182 | | 0.1592 | 3.6474 | 1200 | 0.1470 | 0.2591 | 0.2231 | | 0.1609 | 3.9514 | 1300 | 0.1419 | 0.2816 | 0.2300 | ### Framework versions - Transformers 4.48.1 - Pytorch 2.4.0 - Datasets 3.6.0 - Tokenizers 0.21.4