README.md

metadata

license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-bs-cs-train-noaug-test-noaug
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: cs
          split: None
          args: cs
        metrics:
          - name: Wer
            type: wer
            value: 35.114377279257376

whisper-bs-cs-train-noaug-test-noaug

This model is a fine-tuned version of openai/whisper-base on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3769
• Wer: 35.1144

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3006	1.4440	1000	0.4410	41.9383
0.1741	2.8881	2000	0.3800	36.4792
0.0972	4.3321	3000	0.3750	35.3059
0.079	5.7762	4000	0.3769	35.1144

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1