CoolFace
Modelpublic

simpragma/breeze-listen-dsw-base-ta

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 Tamil - base

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

  • —Loss: 0.375
  • —Wer: 21.4071

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: 1000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.16980.11000.572330.4406
0.35780.22000.430225.6862
0.28320.33000.396723.2048
0.26630.44000.403823.8525
0.51750.55000.396224.1466
0.23650.66000.385022.2595
0.16920.77000.396021.8687
0.18150.88000.382322.0772
0.16120.99000.370121.8056
0.13931.010000.37521.4071

Framework versions

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