metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - abdouaziiz/hausa_unified
metrics:
  - wer
model-index:
  - name: whisper-medium-v3-ha-4
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: abdouaziiz/hausa_unified
          type: abdouaziiz/hausa_unified
        metrics:
          - name: Wer
            type: wer
            value: 0.24580119656887478

whisper-medium-v3-ha-4

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

Loss: 0.3495
Wer: 0.2458

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: 8
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: 50
training_steps: 26000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2577	1.6447	2000	0.3744	0.2884
0.0717	3.2895	4000	0.3495	0.2458
0.0274	4.9342	6000	0.3574	0.2215
0.0073	6.5789	8000	0.3820	0.2155
0.0036	8.2237	10000	0.4093	0.2188

Framework versions

Transformers 4.46.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.20.3