Hugging Face's logo

devkyle
/
whisper-tiny-pure

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-tiny-pure / README.md
devkyle's picture
devkyle
End of training
3bfa208 verified
preview code
|
raw
history blame contribute delete
1.64 kB
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-small-akan
    results: []

whisper-small-akan

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

  • Loss: 1.1252
  • Wer: 48.2062

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: 0.0001
  • 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

Training results

Training Loss Epoch Step Validation Loss Wer
0.1053 10.0 500 0.9054 55.8896
0.0202 20.0 1000 1.0748 53.0428
0.0023 30.0 1500 1.1104 48.8017
0.0003 40.0 2000 1.1252 48.2062

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1