iRaduS/whisper-memory-efficient

1---2library_name: transformers3language:4- ro5license: apache-2.06base_model: openai/whisper-large-v37tags:8- generated_from_trainer9datasets:10- custom11model-index:12- name: Whisper Large v3 RO - finetune13  results: []14---15 16<!-- This model card has been generated automatically according to the information the Trainer had access to. You17should probably proofread and complete it, then remove this comment. -->18 19# Whisper Large v3 RO - finetune20 21This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the custom dataset.22 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 1e-0541- train_batch_size: 842- eval_batch_size: 843- seed: 4244- gradient_accumulation_steps: 3245- total_train_batch_size: 25646- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments47- lr_scheduler_type: linear48- lr_scheduler_warmup_steps: 1049- num_epochs: 850- mixed_precision_training: Native AMP51 52### Training results53 54 55 56### Framework versions57 58- Transformers 4.48.059- Pytorch 2.7.1+cu12660- Datasets 4.0.061- Tokenizers 0.21.262