Whisper base ateso

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

  • Loss: 0.5293
  • Wer: 27.7108

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: 1000
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.4597 3.5 1000 0.5186 32.1285
0.1812 6.99 2000 0.4394 26.7738
0.0429 10.49 3000 0.4765 26.7738
0.016 13.99 4000 0.5157 27.3092
0.0053 17.48 5000 0.5293 27.7108

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
20
Safetensors
Model size
72.6M 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 Eyesiga/whisper_base_ateso

Finetuned
(380)
this model

Evaluation results