Edit model card

pronunciation_accuracy

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: 0.9277
  • Accuracy: 0.623

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 125 0.8216 0.639
No log 2.0 250 0.8341 0.638
No log 3.0 375 0.9277 0.623

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
106
Safetensors
Model size
20.7M params
Tensor type
F32
ยท

Finetuned from

Space using JohnJumon/pronunciation_accuracy 1