README.md

metadata

language:
  - it
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
base_model: openai/whisper-medium
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Mixed-Italian
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_17_0 it
          type: mozilla-foundation/common_voice_17_0
          config: it
          split: test
          args: it
        metrics:
          - type: wer
            value: 6.840122206312234
            name: Wer
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: it_it
          split: test
        metrics:
          - type: wer
            value: 3.75
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: facebook/multilingual_librispeech
          type: facebook/multilingual_librispeech
          config: italian
          split: test
        metrics:
          - type: wer
            value: 11.44
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: facebook/voxpopuli
          type: facebook/voxpopuli
          config: it
          split: test
        metrics:
          - type: wer
            value: 17.94
            name: WER

Whisper Medium Mixed-Italian

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_17_0 it dataset. It achieves the following results on the evaluation set:

• Loss: 0.1318
• Wer: 6.8401

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: 32
• 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
0.1502	0.2	1000	0.1708	9.0922
0.1584	0.4	2000	0.1554	8.1757
0.1309	0.6	3000	0.1426	7.4142
0.0984	0.8	4000	0.1370	7.1298
0.0933	1.0	5000	0.1318	6.8401

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1