Hugging Face's logo

serge-wilson
/
whisper-base-wolof

Automatic Speech Recognition
Transformers
PyTorch
multilingual
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
2
whisper-base-wolof / README.md
serge-wilson's picture
serge-wilson
End of training
da92280
preview code
|
raw history blame
No virus
1.6 kB
metadata
language:
  - multilingual
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Base Wolof
    results: []

Whisper Base Wolof

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2902
  • Wer: 32.8385

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: 500
  • training_steps: 4000

Training results

Training Loss Epoch Step Validation Loss Wer
0.5632 1.14 1000 0.4672 48.8263
0.3464 2.29 2000 0.3461 34.6403
0.2514 3.43 3000 0.3013 32.1406
0.1957 4.57 4000 0.2902 32.8385

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.0
  • Datasets 2.14.5
  • Tokenizers 0.13.3