README.md

metadata

language:
  - ro
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - iulik-pisik/audio_vreme
metrics:
  - wer
model-index:
  - name: Whisper Small Romanian - Vreme Florin Busuioc
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Vreme ProTv - Florin Busuioc
          type: iulik-pisik/audio_vreme
          config: default
          split: None
          args: 'config: ro, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 9.064860640791874

Whisper Small Romanian - Vreme Florin Busuioc

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

• Loss: 0.2208
• Wer: 9.0649

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
0.0103	7.63	1000	0.1628	9.5598
0.0003	15.27	2000	0.2040	9.3514
0.0001	22.9	3000	0.2165	9.0649
0.0001	30.53	4000	0.2208	9.0649

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2