metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-tiny-bg
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: bg
          split: None
          args: bg
        metrics:
          - name: Wer
            type: wer
            value: 58.93870930367281

whisper-tiny-bg

This model is a fine-tuned version of openai/whisper-tiny on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.8746
Wer: 58.9387

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
optimizer: Use 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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3458	3.6630	1000	0.7458	60.0684
0.1146	7.3260	2000	0.7719	58.7417
0.0475	10.9890	3000	0.8278	57.8149
0.0245	14.6520	4000	0.8746	58.9387

Framework versions

Transformers 4.46.1
Pytorch 2.4.1+cu121
Datasets 3.0.2
Tokenizers 0.20.1