metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: openai-whisper-tiny-es_ecu911-PasoBajo
    results: []

openai-whisper-tiny-es_ecu911-PasoBajo

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.4352
Wer: 99.8848

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
1.4814	2.6596	500	1.5305	106.1444
0.7838	5.3191	1000	1.3791	102.5922
0.5823	7.9787	1500	1.4044	110.1190
0.4573	10.6383	2000	1.4352	99.8848

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1