README.md

metadata

language:
  - nyn
license: apache-2.0
base_model: openai/whisper-small
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - tericlabs
metrics:
  - wer
model-index:
  - name: Whisper Small Runyankore
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Yogera data
          type: tericlabs
          config: nyn
          split: test
          args: nyn
        metrics:
          - name: Wer
            type: wer
            value: 55.483106105512746

Whisper Small Runyankore

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

• Loss: 1.3134
• Wer: 55.4831

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: 1000
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5152	13.01	1000	1.2299	59.1583
0.0054	26.02	2000	1.3134	55.4831

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0