CoolFace
Modelpublic

UsmanAXAI/whisper-small-ft-client

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes4downloads
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 small Ar - AxAI

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

  • —Loss: 1.5990
  • —Wer: 84.1146

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: 2
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.80446.372001.241769.9219
0.03612.754001.179160.9375
0.010819.126001.312880.2083
0.003525.58001.364162.6953
0.000931.8710001.406666.6016
0.000438.2512001.441064.5833
0.000344.6214001.471263.3464
0.000251.016001.492763.6068
0.000257.3718001.510267.1875
0.000263.7520001.525466.6016
0.000170.1222001.539377.8646
0.000176.4924001.551277.9297
0.000182.8726001.561677.7344
0.000189.2428001.571083.1380
0.000195.6230001.579188.0859
0.0001101.9932001.585488.1510
0.0001108.3734001.591088.0859
0.0001114.7436001.595384.1146
0.0001121.1238001.597884.1797
0.0001127.4940001.599084.1146

Framework versions

  • —Transformers 4.37.2
  • —Pytorch 2.2.0+cu121
  • —Datasets 2.17.1
  • —Tokenizers 0.15.2