Hugging Face's logo

hypaai
/
hypaai-whisper-small-v1-04272025

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files Metrics Community
hypaai-whisper-small-v1-04272025 / README.md
hypaai's picture
hypaai
Update README.md
27c1320 verified
preview code
|
raw
history blame contribute delete
1.38 kB
metadata
library_name: transformers
language:
  - ig
  - yo
  - en
  - ha
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
model-index:
  - name: hypaai-whisper-small-v1-04272025
    results: []
datasets:
  - hypaai/original_wspr_data_wspr
  - hypaai/afrispeech_en_ng_wspr

wspr_wazobia_run1_04272025

This model is a fine-tuned version of openai/whisper-small on the None dataset.

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 OptimizerNames.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: 1000
  • training_steps: 12000
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.1