metadata

language:
  - ro
license: apache-2.0
base_model: openai/whisper-base
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - iulik-pisik/horoscop_neti
metrics:
  - wer
model-index:
  - name: Whisper Base Romanian - Horoscop Neti
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Horoscop Neti
          type: iulik-pisik/horoscop_neti
          config: default
          split: None
          args: 'config: ro, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 17.035775127768314

Whisper Base Romanian - Horoscop Neti

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

Loss: 0.3282
Wer: 17.0358

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
0.0142	9.71	1000	0.2707	18.0336
0.0012	19.42	2000	0.3073	17.0601
0.0007	29.13	3000	0.3225	17.0114
0.0005	38.83	4000	0.3282	17.0358

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2