README.md

metadata

library_name: transformers
language:
  - sw
base_model: EYEDOL/SALAMA_C3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
model-index:
  - name: ASR_FROM_C3_NEW
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 13.0
          type: mozilla-foundation/common_voice_13_0
          config: sw
          split: None
          args: 'config: sw, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 15.162401781587462

ASR_FROM_C3_NEW

This model is a fine-tuned version of EYEDOL/SALAMA_C3 on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1985
• Wer: 15.1624

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: Use OptimizerNames.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: 500
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1562	0.6918	2000	0.1985	15.1624

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2