Edit model card

whisper-large-v3-finetuned-2

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

  • Loss: 1.8292
  • Wer: 29.2595

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-09
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Wer
1.0224 1.0 7532 1.8944 30.6810
2.932 2.0 15064 1.8575 30.1652
1.6702 3.0 22596 1.8380 29.3775
1.9191 4.0 30128 1.8304 29.2800
2.155 5.0 37660 1.8292 29.2595

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
6
Safetensors
Model size
1.54B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tkwon4/whisper-large-v3-finetuned-2

Finetuned
(298)
this model