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: fa_ir
          split: None
          args: 'config: it split: test'
        metrics:
          - type: wer
            value: 36.47645153251931
            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: 0.5897
Wer: 36.4765

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
0.175	4.6083	1000	0.4024	37.5480
0.0198	9.2166	2000	0.4795	36.7555
0.0039	13.8249	3000	0.5412	37.0297
0.0018	18.4332	4000	0.5772	36.4017
0.0013	23.0415	5000	0.5897	36.4765

Framework versions

Transformers 4.43.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1