CoolFace
Modelpublic

UDA-LIDI/openai-whisper-large-v3-fullFT-es_ecu911_V2martin_win30s_samples

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes6downloads
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. -->

Whisper openai-whisper-large-v3

This model is a fine-tuned version of openai/whisper-large-v3 on the llamadas ecu911 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2501
  • —Wer: 19.6292

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: 2e-05
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 8
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: constant
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.50571.04220.338035.0250
0.20612.08440.245832.0536
0.11363.012660.227026.1110
0.06854.016880.228117.5388
0.04445.021100.224818.6169
0.03016.025320.247018.6037
0.02347.029540.242018.1699
0.0198.033760.236821.5751
0.01639.037980.234615.9216
0.014210.042200.250119.6292

Framework versions

  • —Transformers 4.45.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.0.1
  • —Tokenizers 0.20.1