CoolFace
Modelpublic

macarious/torgo_xlsr_finetune_F04_old

sourceHugging Faceapache-2.0updated 3y 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. -->

torgoxlsrfinetune_F04

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.6313
  • —Wer: 0.3274

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: 0.0001
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 8
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 1000
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossWer
3.50750.9510003.33521.0
1.82541.8920001.74120.8714
0.87492.8430001.50340.6508
0.66213.7840001.84310.5925
0.52114.7350001.47490.4916
0.43215.6860001.43540.4748
0.37396.6270001.52450.4580
0.33327.5780001.57740.4550
0.30288.5190001.64060.3887
0.28289.46100001.46220.3867
0.258810.41110001.58110.3689
0.252211.35120001.63370.3739
0.230312.3130001.51850.3531
0.224913.24140001.47980.3521
0.200214.19150001.98130.3818
0.192415.14160001.82370.3709
0.182416.08170001.63720.3373
0.162817.03180001.82130.3482
0.165217.97190001.63520.3403
0.152118.92200001.66900.3383
0.156419.87210001.63130.3274

Framework versions

  • —Transformers 4.26.1
  • —Pytorch 2.2.0
  • —Datasets 2.16.1
  • —Tokenizers 0.13.3