README.md

metadata

library_name: transformers
language:
  - sr
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper - Serbian Model
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: sr
          split: None
          args: sr
        metrics:
          - name: Wer
            type: wer
            value: 56.56320443904976

Whisper - Serbian Model

This model is a fine-tuned version of openai/whisper-small on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4861
• Wer: 56.5632

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: 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
0.0342	4.6083	1000	0.3222	50.6849
0.0021	9.2166	2000	0.4106	54.8119
0.0003	13.8249	3000	0.4800	55.0893
0.0002	18.4332	4000	0.4861	56.5632

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.20.1