README.md

metadata

language:
  - pt
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
base_model: openai/whisper-medium
datasets:
  - mozilla-foundation/common_voice_17_0
  - google/fleurs
  - facebook/multilingual_librispeech
metrics:
  - wer
model-index:
  - name: Whisper Medium Mixed-Portuguese
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_17_0 pt
          type: mozilla-foundation/common_voice_17_0
          config: pt
          split: test
          args: pt
        metrics:
          - type: wer
            value: 7.122989865404904
            name: Wer
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: pt_br
          split: test
        metrics:
          - type: wer
            value: 8.1
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: facebook/multilingual_librispeech
          type: facebook/multilingual_librispeech
          config: portuguese
          split: test
        metrics:
          - type: wer
            value: 13.57
            name: WER
pipeline_tag: automatic-speech-recognition

Whisper Medium Mixed-Portuguese

This model is a fine-tuned version of openai/whisper-medium on the pt datasets:

• mozilla-foundation/common_voice_17_0
• google/fleurs
• facebook/multilingual_librispeech

It achieves the following results on the evaluation set:

• Loss: 0.1353
• Wer: 7.1230

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
0.1116	0.2	1000	0.1570	8.5824
0.105	0.4	2000	0.1484	7.9398
0.0783	0.6	3000	0.1374	7.4475
0.1703	0.8	4000	0.1370	7.2413
0.0977	1.0622	5000	0.1353	7.1230

Framework versions

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