train-data / README.md
Aynursusuz's picture
Model save
095e245 verified
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: train-data
    results: []

train-data

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

  • Loss: 0.0341
  • Accuracy: 0.9934
  • Precision: 0.9934
  • Recall: 0.9934
  • F1: 0.9934
  • Music Precision: 0.9910
  • Music Recall: 1.0
  • Music F1: 0.9955

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: 32
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1 Music Precision Music Recall Music F1
0.0148 5.2632 100 0.0020 1.0 1.0 1.0 1.0 1.0 1.0 1.0
0.0021 10.5263 200 0.0341 0.9934 0.9934 0.9934 0.9934 0.9910 1.0 0.9955

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.5.1+cu121
  • Datasets 4.3.0
  • Tokenizers 0.22.1