README.md

metadata

license: apache-2.0
base_model: Akashpb13/Swahili_xlsr
tags:
  - generated_from_trainer
datasets:
  - ml-superb-subset
metrics:
  - wer
model-index:
  - name: xho-2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ml-superb-subset
          type: ml-superb-subset
          config: xho
          split: test
          args: xho
        metrics:
          - name: Wer
            type: wer
            value: 0.6780487804878049

xho-2

This model is a fine-tuned version of Akashpb13/Swahili_xlsr on the ml-superb-subset dataset. It achieves the following results on the evaluation set:

• Loss: 0.7671
• Wer: 0.6780

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.033	15.3846	400	0.7671	0.6780

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1