Hugging Face's logo

ngia
/
whisper-small-wolof-v2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
French
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-wolof-v2 / README.md
ngia's picture
ngia
End of training
adf3131 verified
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
library_name: transformers
language:
  - fr
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - IndabaxSenegal/asr-wolof-dataset
model-index:
  - name: Whisper Small WO - Team
    results: []

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:

  • eval_loss: 1.8224
  • eval_wer: 111.3192
  • eval_runtime: 3443.366
  • eval_samples_per_second: 0.754
  • eval_steps_per_second: 0.094
  • epoch: 1.5385
  • step: 1000

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: 2000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0