metadata

library_name: transformers
language:
  - sw
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Imla Custom
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: sw
          split: None
          args: 'config: sw, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 21.894613421615283

Whisper Imla Custom

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3255
Wer: 21.8946

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
0.3114	0.4342	1000	0.4283	28.0065
0.267	0.8684	2000	0.3515	25.2224
0.1433	1.3026	3000	0.3472	22.0142
0.1385	1.7369	4000	0.3255	21.8946

Framework versions

Transformers 4.45.2
Pytorch 2.1.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1