CoolFace
Modelpublic

UDA-LIDI/openai-whisper-large-LoRA32-es_ecu911_adapter

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes5downloads
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-LoRA32-es_ecu911

This model is a fine-tuned version of openai/whisper-large on the llamadas ecu9111 segmentos dmarquez dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7446

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: 0.0002
  • —trainbatchsize: 8
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 50
  • —num_epochs: 5
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
1.2531.0531.0113
0.74432.01060.7473
0.67613.01590.7312
0.61564.02120.7381
0.53845.02650.7446

Framework versions

  • —PEFT 0.13.2
  • —Transformers 4.45.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.0.1
  • —Tokenizers 0.20.1