CoolFace
Modelpublic

Hanhpt23/whisper-small-chinesemed-free_E3-11

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes12downloads
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/ChiMed dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.1603
  • —Wer: 84.4794
  • —Cer: 25.0446

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 LossWerCer
0.65171.01610.8312272.4951128.1194
0.34212.03220.7985171.119863.7478
0.22063.04830.9271152.062959.8039
0.1034.06441.039785.265228.4091
0.08345.08051.033592.730826.6266
0.05786.09661.089386.247528.6319
0.06177.011271.124388.212228.0303
0.04078.012881.157784.675828.6988
0.0329.014491.184783.300626.7157
0.022310.016101.140494.106132.5980
0.014411.017711.192788.015728.3645
0.008712.019321.130988.408626.4483
0.012613.020931.161384.086425.5570
0.004714.022541.186386.444025.7353
0.006115.024151.167483.693527.0276
0.001316.025761.176283.497125.2005
0.000717.027371.169784.872325.4679
0.000618.028981.161483.890025.2897
0.000219.030591.159784.479425.0446
0.000220.032201.160384.479425.0446

Framework versions

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