Hugging Face's logo

anggiatm
/
whisper-small-id-finetune

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-id-finetune / README.md
anggiatm's picture
anggiatm
End of training
a65b012 verified
preview code
|
raw
history blame contribute delete
1.68 kB
metadata
library_name: transformers
license: apache-2.0
base_model: anggiatm/whisper-small-id
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-small-id-finetune
    results: []

whisper-small-id-finetune

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

  • Loss: 0.1926
  • Wer: 8.7727

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0065 6.0606 1000 0.1839 9.0201
0.0008 12.1212 2000 0.1849 8.3994
0.0005 18.1818 3000 0.1904 8.7634
0.0004 24.2424 4000 0.1926 8.7727

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1