Hugging Face's logo

Mayalina
/
whisper-tiny-akan

TensorBoard
Safetensors
Akan
whisper
Generated from Trainer
Model card Files Metrics Community
whisper-tiny-akan / README.md
Mayalina's picture
Mayalina
Update with WER score
a4f278b verified
preview code
|
raw
history blame contribute delete
No virus
1.43 kB
metadata
language:
  - ak
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - UGSPEECHDATA
model-index:
  - name: Whisper Tiny Ak - Sumaya Ahmed Salihs
    results: []

Whisper Tiny Ak - Sumaya Ahmed Salihs

This model is a fine-tuned version of openai/whisper-tiny on the openai/whisper-tiny dataset. It achieves the following results on the evaluation set: WER: 0.931

  • eval_loss: 4.6150
  • eval_runtime: 94.5398
  • eval_wer: 0.9308
  • eval_samples_per_second: 0.529
  • eval_steps_per_second: 0.529
  • step: 0

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: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1