Edit model card

Large V3 Turbo Stutter - Ariel Cerda

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Libristutter 4.7k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5114
  • Wer: 24.2314

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
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0584 3.7453 1000 0.3100 20.0250
0.0117 7.4906 2000 0.3970 21.1392
0.002 11.2360 3000 0.4427 20.3825
0.0003 14.9813 4000 0.4927 23.8501
0.0002 18.7266 5000 0.5114 24.2314

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1
Downloads last month
9
Safetensors
Model size
809M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for arielcerdap/largev3-turbo-stutter

Finetuned
(74)
this model

Dataset used to train arielcerdap/largev3-turbo-stutter

Evaluation results