Whisper Large V2

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4524
  • Wer: 15.0055

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 20
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Wer
0.777 0.55 30 0.4578 22.6024
0.3606 1.09 60 0.4063 15.0683
0.213 1.64 90 0.4164 20.4050
0.1713 2.18 120 0.4208 27.9705
0.1004 2.73 150 0.4064 16.2612
0.0653 3.27 180 0.4389 15.5078
0.0404 3.82 210 0.4356 14.3149
0.024 4.36 240 0.4477 14.3776
0.0158 4.91 270 0.4524 15.0055

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.0
Downloads last month
19
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 golesheed/whisper-non-native-adult-2-dutch

Finetuned
(191)
this model