metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny.en
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - eai6/bungoma_training
metrics:
  - wer
model-index:
  - name: Whisper tiny
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Nyansapo AI Dataset
          type: eai6/bungoma_training
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 379.5513373597929

Whisper tiny

This model is a fine-tuned version of openai/whisper-tiny.en on the Nyansapo AI Dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.4549
Wer: 379.5513

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: 250
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.2224	1.38	250	0.6100	153.0630
0.545	2.76	500	0.0995	662.3814
0.2906	4.14	750	0.0822	650.7334
0.2063	5.52	1000	0.4549	379.5513

Framework versions

Transformers 4.39.1
Pytorch 2.2.1
Datasets 2.18.0
Tokenizers 0.15.2