CoolFace
Modelpublic

allenpoe/whisper-base-atco-converted

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes2downloads
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 Base ATCOSIM

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

  • —Loss: 0.0770
  • —Wer: 4.9143

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: 1e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 1000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
1.8820.20921001.529067.4143
0.43340.41842000.425126.2587
0.18830.62763000.221815.5932
0.12590.83684000.148710.9869
0.07131.04605000.11689.4135
0.04461.25526000.10367.5656
0.06521.46447000.09196.3203
0.05081.67368000.08295.1152
0.0381.88289000.07764.9009
0.01862.092110000.07704.9143

Framework versions

  • —Transformers 4.42.0.dev0
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.19.2
  • —Tokenizers 0.19.1