README.md

metadata

language:
  - sr
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Small Sr Fleurs- Sagicc
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Google Fleurs
          type: google/fleurs
          config: sr_rs
          split: test
          args: sr_rs
        metrics:
          - name: Wer
            type: wer
            value: 25.6021212344406

Whisper Small Sr Fleurs- Sagicc

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

• Loss: 0.4134
• Wer Ortho: 28.9292
• Wer: 25.6021

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0649	2.49	500	0.3685	30.6352	27.1489
0.0181	4.98	1000	0.4134	28.9292	25.6021

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3