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: 0.4378
  • Wer: 19.2034

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
0.7537 0.55 30 0.4344 40.1612
0.3924 1.09 60 0.3993 40.9199
0.2148 1.64 90 0.3921 22.2538
0.1731 2.18 120 0.4108 21.7955
0.0933 2.73 150 0.3953 20.7523
0.0682 3.27 180 0.4179 17.2594
0.0377 3.82 210 0.4136 17.3226
0.0227 4.36 240 0.4298 20.0411
0.0137 4.91 270 0.4378 19.2034

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.0
Downloads last month
20
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-9-dutch

Finetuned
(191)
this model