Hugging Face's logo

ngia
/
whisper-small-wo

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
French
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Whisper Small WO - Team

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

  • Loss: 0.1726
  • Wer: 78.4437

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 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
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0965 1.5408 1000 0.1751 83.2067
0.0406 3.0817 2000 0.1761 78.6749
0.0192 4.6225 3000 0.1772 78.8612
0.0037 6.1633 4000 0.1726 78.4437

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.4.0
  • Datasets 3.1.0
  • Tokenizers 0.20.0
Downloads last month
-
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ngia/whisper-small-wo

Base model

openai/whisper-small
Finetuned
(3502)
this model

Dataset used to train ngia/whisper-small-wo

Evaluation results