Edit model card

whisper-tiny-minds-v5-numproc1

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6530
  • Wer Ortho: 0.4102
  • Wer: 0.3751

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.4354 3.57 100 0.5542 0.4539 0.3870
0.066 7.14 200 0.5501 0.4059 0.3554
0.0086 10.71 300 0.6204 0.3953 0.3542
0.0028 14.29 400 0.6455 0.3990 0.3631
0.0022 17.86 500 0.6530 0.4102 0.3751

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3
Downloads last month
18
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.

Dataset used to train MariaK/whisper-tiny-minds-v5-numproc1

Evaluation results