Edit model card

Whisper Small Romanian - Horoscop Neti

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

  • Loss: 0.2392
  • Wer: 9.7834

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0066 9.71 1000 0.1934 10.0754
0.0003 19.42 2000 0.2242 9.5157
0.0002 29.13 3000 0.2351 9.6861
0.0002 38.83 4000 0.2392 9.7834

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2
Downloads last month
3
Safetensors
Model size
242M 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 iulik-pisik/horoscope_model_small

Finetuned
(1831)
this model
Finetunes
1 model

Dataset used to train iulik-pisik/horoscope_model_small

Evaluation results