Edit model card

whisper-base-atco2-asr

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

  • Loss: 0.9060
  • Wer: 49.2883

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-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Wer
0.9897 12.5 50 0.8748 70.4626
0.0447 25.0 100 0.8519 52.0463
0.0087 37.5 150 0.8772 39.2794
0.0043 50.0 200 0.8891 39.3683
0.0034 62.5 250 0.8976 49.4217
0.0027 75.0 300 0.9022 49.1548
0.0024 87.5 350 0.9050 49.2438
0.0023 100.0 400 0.9060 49.2883

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
0
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference API
or
This model can be loaded on Inference API (serverless).

Finetuned from