README.md

metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: EYEDOL/english-ASR
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - okezieowen/misc_naija_english_audio
metrics:
  - wer
model-index:
  - name: English_ASR2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: misc_naija_english
          type: okezieowen/misc_naija_english_audio
        metrics:
          - name: Wer
            type: wer
            value: 0.8855441714268444

English_ASR2

This model is a fine-tuned version of EYEDOL/english-ASR on the misc_naija_english dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001
• Wer: 0.8855

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	8.9286	3000	0.0001	0.8855

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1