Willy030125/whisper_large_v3_turbo_finetuned_en_id_v1

<!-- 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. -->

whisperlargev3turbofinetunedenid_v1

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the several datasets. It achieves the following results on the evaluation set:

• —eval_loss: 0.1362
• —eval_runtime: 263.9538
• —evalsamplesper_second: 5.906
• —evalstepsper_second: 5.906
• —epoch: 3 (checkpoint model)
• —step: 687 (checkpoint model)

Training and Evaluation Data

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 1e-05
• —trainbatchsize: 8
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 100
• —num_epochs: 25

Framework versions

• —Transformers 4.41.2
• —Pytorch 2.2.2+cu121
• —Datasets 2.18.0
• —Tokenizers 0.19.1