README.md

metadata

language:
  - pl
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
  - google/fleurs
metrics:
  - wer
base_model: openai/whisper-medium
model-index:
  - name: Whisper Medium PL
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: pl
          split: test
          args: pl
        metrics:
          - type: wer
            value: 8.71
            name: WER
          - type: wer_without_norm
            value: 22
            name: WER unnormalized
          - type: cer
            value: 2.41
            name: CER
          - type: mer
            value: 8.65
            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: 11.99
            name: WER
          - type: wer_without_norm
            value: 30.9
            name: WER unnormalized
          - type: cer
            value: 6.54
            name: CER
          - type: mer
            value: 11.68
            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: 10.89
            name: WER
          - type: wer_without_norm
            value: 30.7
            name: WER unnormalized
          - type: cer
            value: 4.04
            name: CER
          - type: mer
            value: 10.8
            name: MER

Whisper Medium PL

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

• Loss: 0.3947
• Wer: 8.6872

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: 4
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0805	0.48	500	0.2556	10.4888
0.0685	0.96	1000	0.2462	10.7608
0.0356	1.45	1500	0.2561	9.6728
0.0337	1.93	2000	0.2327	9.6459
0.017	2.41	2500	0.2444	9.9464
0.0179	2.9	3000	0.2554	9.6476
0.0056	3.38	3500	0.3001	9.3638
0.007	3.86	4000	0.2809	9.2245
0.0033	4.34	4500	0.3235	9.3437
0.0024	4.83	5000	0.3148	9.0633
0.0008	5.31	5500	0.3416	9.0112
0.0011	5.79	6000	0.3876	9.1858
0.0004	6.27	6500	0.3745	8.7292
0.0003	6.76	7000	0.3704	9.0314
0.0003	7.24	7500	0.3929	8.6553
0.0002	7.72	8000	0.3947	8.6872

Framework versions

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