Edit model card

Whisper Small Indonesian

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2467
  • Wer: 14.5388

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: 8
  • eval_batch_size: 4
  • 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: 5000

Training results

Training Loss Epoch Step Validation Loss Wer
0.8102 0.15 1000 0.3228 18.7532
0.6991 0.29 2000 0.2806 16.6552
0.6588 0.44 3000 0.2646 14.8838
0.6162 0.58 4000 0.2540 14.6262
0.5996 0.73 5000 0.2467 14.5388

Framework versions

  • Transformers 4.31.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3
Downloads last month
12
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for TheRains/cv9-special-batch8-small-concat-YT-NotClean

Finetuned
(1849)
this model

Dataset used to train TheRains/cv9-special-batch8-small-concat-YT-NotClean

Evaluation results