metadata

library_name: transformers
language:
  - es
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small 200 Sep 6 speedy es - Jessica Martinez
    results: []

Whisper Small 200 Sep 6 speedy es - Jessica Martinez

This model is a fine-tuned version of openai/whisper-small on the procesar-videos2024rdm200speedy dataset. It achieves the following results on the evaluation set:

Loss: 0.5645
Wer: 24.7788

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: 25
training_steps: 200
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3473	4.1667	50	0.5393	26.8538
0.0903	8.3333	100	0.5190	29.6308
0.018	12.5	150	0.5598	24.8398
0.0082	16.6667	200	0.5645	24.7788

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1