CoolFace
Modelpublic

flima/openai-whisper-large-v2-fullFT-es_ecu911_V2martin_win30s_samples

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. -->

Whisper openai-whisper-large-v2

This model is a fine-tuned version of openai/whisper-large-v2 on the llamadas ecu911 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2832
  • —Wer: 19.8947

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
0.52571.04220.359635.3561
0.21082.08440.288827.7362
0.11533.012660.269425.3256
0.06744.016880.281032.9731
0.04355.021100.281720.3380
0.03016.025320.291023.0673
0.02457.029540.281720.5043
0.0218.033760.273418.4400
0.01739.037980.278423.9263
0.016710.042200.283219.8947

Framework versions

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