README.md

metadata

language:
  - it
license: apache-2.0
base_model: openai/whisper-small
tags:
  - it-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small IT - GoodOnions
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: it
          split: test[:2500]
          args: 'config: it, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 83.94127565077929

Whisper Small IT - GoodOnions

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4681
• Wer: 83.9413

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
0.1517	1.6	1000	0.3859	227.6309
0.0313	3.2	2000	0.4126	50.3681
0.0156	4.8	3000	0.4367	67.6440
0.0038	6.4	4000	0.4681	83.9413

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0