CoolFace
Modelpublic

Hanhpt23/whisper-base-frenchmed-v1

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes346downloads
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-base

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

  • —Loss: 1.5990
  • —Wer: 44.8680

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
1.13281.02151.072753.9589
0.70152.04301.118559.4575
0.37273.06451.158046.9208
0.18594.08601.275763.0499
0.09965.010751.367443.6950
0.06196.012901.391648.2405
0.04597.015051.430544.8680
0.03428.017201.455547.1408
0.03239.019351.479245.0880
0.014110.021501.541448.8270
0.010911.023651.557544.5748
0.006412.025801.549945.5279
0.006113.027951.543945.6012
0.008114.030101.567946.6276
0.001315.032251.571446.9941
0.002816.034401.577744.6481
0.001917.036551.590445.7478
0.000618.038701.593143.9150
0.000419.040851.598144.5015
0.000420.043001.599044.8680

Framework versions

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