metadata

library_name: transformers
language:
  - ha
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - Seon25/common_voice_16_0_
metrics:
  - wer
model-index:
  - name: Whisper Small Ha - Eldad Akhaumere
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.0
          type: Seon25/common_voice_16_0_
          config: ha
          split: None
          args: 'config: ha, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 108.10546875

Whisper Small Ha - Eldad Akhaumere

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

Loss: 4.9575
Wer Ortho: 110.3468
Wer: 108.1055

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: 0.0005
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
num_epochs: 13.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
1.5785	3.1847	500	3.8839	99.5593	99.8438
1.1623	6.3694	1000	4.4847	97.7582	98.0078
0.9893	9.5541	1500	4.7922	108.7373	107.6172
0.8816	12.7389	2000	4.9575	110.3468	108.1055

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1