metadata

language:
  - ro
license: apache-2.0
base_model: iulik-pisik/horoscope_model_tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - iulik-pisik/audio_vreme
metrics:
  - wer
model-index:
  - name: Horoscope Model Tiny - finetuned on weather
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Vreme ProTV
          type: iulik-pisik/audio_vreme
          config: default
          split: test
          args: 'config: ro, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 13.995067817509248

Horoscope Model Tiny - finetuned on weather

This model is a fine-tuned version of iulik-pisik/horoscope_model_tiny on the Vreme ProTV dataset. It achieves the following results on the evaluation set:

Loss: 0.2868
Wer: 13.9951

Model description

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
0.0443	6.02	1000	0.1949	15.5569
0.0023	12.05	2000	0.2601	14.1389
0.0008	18.07	3000	0.2798	14.0362
0.0006	24.1	4000	0.2868	13.9951

Framework versions

Transformers 4.39.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2