README.md

metadata

library_name: transformers
language:
  - sw
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - DigitalUmuganda/AfriVoice
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Sanchit Gandhi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: AfriVoice
          type: DigitalUmuganda/AfriVoice
          args: 'config: sw, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 35.83130951004202

Whisper Small Hi - Sanchit Gandhi

This model is a fine-tuned version of openai/whisper-small on the AfriVoice dataset. It achieves the following results on the evaluation set:

• Loss: 0.8767
• Wer: 35.8313

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: 16
• 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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0665	8.1633	1000	0.7047	36.8683
0.0023	16.3265	2000	0.8767	35.8313

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1