Edit model card

Whisper openai-whisper-large-v3

This model is a fine-tuned version of openai/whisper-large-v3 on the llamadas ecu911 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2409
  • Wer: 69.6717

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: 2
  • eval_batch_size: 1
  • 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: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.3656 2.6596 500 0.7653 44.0256
0.0496 5.3191 1000 0.9726 42.1605
0.0115 7.9787 1500 1.1578 111.6961
0.0015 10.6383 2000 1.2409 69.6717

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
89
Safetensors
Model size
1.54B 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 UDA-LIDI/openai-whisper-large-v3-es_ecu911

Finetuned
(319)
this model

Collection including UDA-LIDI/openai-whisper-large-v3-es_ecu911