Hugging Face's logo

bhattasp
/
whisper-finetuned-bial2

TensorBoard
Safetensors
English
whisper
Generated from Trainer
Model card Files Metrics Community
whisper-finetuned-bial2 / README.md
bhattasp's picture
bhattasp
End of training
5800074 verified
preview code
|
raw
history blame contribute delete
No virus
1.54 kB
metadata
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: bhattasp/whisper-finetuned-bial2
    results: []

bhattasp/whisper-finetuned-bial2

This model is a fine-tuned version of openai/whisper-tiny on the bial2 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3088
  • Wer: 29.3953

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

Training results

Training Loss Epoch Step Validation Loss Wer
0.1482 4.3290 1000 0.3253 31.3301
0.0563 8.6580 2000 0.3088 29.3953

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1