README.md

metadata

language:
  - ro
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - iulik-pisik/audio_vreme
metrics:
  - wer
model-index:
  - name: Whisper Tiny Romanian - Vreme
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Vreme ProTv
          type: iulik-pisik/audio_vreme
          config: default
          split: None
          args: 'config: ro, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 13.912864775996711

Whisper Tiny Romanian - Vreme

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

• Loss: 0.2668
• Wer: 13.9129

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
0.0494	6.02	1000	0.1717	14.1184
0.0033	12.05	2000	0.2362	14.3855
0.0011	18.07	3000	0.2596	13.9540
0.0008	24.1	4000	0.2668	13.9129

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2