README.md

metadata

language:
  - pl
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
  - google/fleurs
base_model: openai/whisper-small
model-index:
  - name: Whisper Small PL
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          config: pl
          split: test
        metrics:
          - type: wer
            value: 14.57
            name: WER
          - type: wer_without_norm
            value: 33.57
            name: WER unnormalized
          - type: cer
            value: 4.02
            name: CER
          - type: mer
            value: 14.37
            name: MER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: facebook/voxpopuli
          type: facebook/voxpopuli
          config: pl
          split: test
        metrics:
          - type: wer
            value: 15.73
            name: WER
          - type: wer_without_norm
            value: 34.51
            name: WER unnormalized
          - type: cer
            value: 7.73
            name: CER
          - type: mer
            value: 15.28
            name: MER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: pl_pl
          split: test
        metrics:
          - type: wer
            value: 16.79
            name: WER
          - type: wer_without_norm
            value: 35.69
            name: WER unnormalized
          - type: cer
            value: 4.99
            name: CER
          - type: mer
            value: 16.55
            name: MER

Whisper Small PL

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

• eval_loss: 0.3571
• eval_wer: 14.8004
• eval_runtime: 2233.4204
• eval_samples_per_second: 3.714
• eval_steps_per_second: 0.232
• epoch: 4.03
• step: 3000

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: 24
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 48
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 8000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2