Edit model card

Whisper Base Ru

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3220
  • Wer: 26.0941

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.3017 0.9847 1000 0.3557 28.9880
0.2071 1.9695 2000 0.3259 26.9671
0.1581 2.9542 3000 0.3197 26.2272
0.1152 3.9389 4000 0.3220 26.0941

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
18
Safetensors
Model size
72.6M params
Tensor type
F32
·

Finetuned from

Dataset used to train olafenok/whisper-base-ru

Evaluation results