metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Spanish_english
metrics:
  - wer
model-index:
  - name: Whisper tiny Russian (Trained with Spanish accent)
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Spanish English
          type: Spanish_english
          args: 'config: default, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 16.29353233830846

Whisper tiny Russian (Trained with Spanish accent)

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

Loss: 0.2750
Wer: 16.2935

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: 2
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 1500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4622	0.4864	500	0.3288	17.9851
0.2832	0.9728	1000	0.2934	17.0896
0.1902	1.4591	1500	0.2750	16.2935

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1