CoolFace
Modelpublic

simpragma/breeze-listen-dsw-base-id

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
1likes10downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Breeze DSW Indonesian - base

This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/commonvoice16_0 id dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5347
  • —Wer: 32.8273

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
  • —trainbatchsize: 32
  • —evalbatchsize: 16
  • —seed: 42
  • —distributed_type: multi-GPU
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 2000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.54521.022000.546435.1688
0.34452.044000.540534.0694
0.13973.076000.534732.8273
0.09885.018000.565435.6749
0.0776.0310000.578633.9452
0.03387.0512000.605033.9820
0.01378.0814000.622134.1016
0.015310.0216000.643133.9038
0.012511.0418000.651433.7520
0.009212.0620000.652833.8256

Framework versions

  • —Transformers 4.37.0.dev0
  • —Pytorch 2.1.2+cu121
  • —Datasets 2.16.2.dev0
  • —Tokenizers 0.15.0