CoolFace
Modelpublic

sanchit-gandhi/whisper-medium-es-5k-1e-5-bs-32-no-warmup

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes10downloads
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 Es - Sanchit Gandhi

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

  • —Loss: 0.1024
  • —Wer: 4.1243

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: 4
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —training_steps: 5000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.18870.210000.13295.4249
0.1230.420000.12124.9639
0.15940.630000.11444.3210
0.17770.840000.11164.5379
0.24691.050000.10244.1243

Framework versions

  • —Transformers 4.25.0.dev0
  • —Pytorch 1.12.0
  • —Datasets 2.6.2.dev0
  • —Tokenizers 0.12.1