metadata

base_model: openai/whisper-tiny
datasets:
  - fleurs
language:
  - it
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Tiny Italian 5k - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: it_it
          split: None
          args: 'config: it split: test'
        metrics:
          - type: wer
            value: 50.93909245328804
            name: Wer

Whisper Tiny Italian 5k - Chee Li

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

Loss: 0.6896
Wer: 50.9391

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: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.195	4.6729	1000	0.4900	53.7054
0.0248	9.3458	2000	0.5791	61.4365
0.0076	14.0187	3000	0.6469	54.1907
0.0044	18.6916	4000	0.6788	51.7641
0.0036	23.3645	5000	0.6896	50.9391

Framework versions

Transformers 4.43.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1