CoolFace
Modelpublic

Hanhpt23/whisper-small-Encode-engmed

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes7downloads
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. -->

openai/whisper-small

This model is a fine-tuned version of openai/whisper-small on the pphuc25/EngMed dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.2775
  • —Wer: 25.8817

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: 0.0001
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 100
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossWer
0.81491.034910.896843.5550
0.51262.069820.880535.9730
0.33083.0104730.917336.4008
0.24124.0139640.981433.9519
0.16675.0174551.040031.9450
0.10016.0209461.090333.1316
0.0797.0244371.119133.2309
0.07518.0279281.158029.3991
0.05159.0314191.172329.8778
0.039510.0349101.187629.4972
0.031311.0384011.230528.8578
0.012912.0418921.234427.5577
0.020713.0453831.252729.9002
0.016914.0488741.249827.3969
0.005515.0523651.260427.4277
0.00316.0558561.262726.8923
0.001117.0593471.270026.9135
0.001318.0628381.269527.4785
0.000119.0663291.280426.2836
0.020.0698201.277525.8817

Framework versions

  • —Transformers 4.41.1
  • —Pytorch 2.3.0
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1