README.md

metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_9_0
metrics:
  - wer
model-index:
  - name: cv9-special-batch8-lr3-small
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_9_0
          type: common_voice_9_0
          config: id
          split: test
          args: id
        metrics:
          - name: Wer
            type: wer
            value: 104.82631700023003

cv9-special-batch8-lr3-small

This model is a fine-tuned version of openai/whisper-small on the common_voice_9_0 dataset. It achieves the following results on the evaluation set:

• Loss: 2.7744
• Wer: 104.8263

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: 0.001
• train_batch_size: 8
• eval_batch_size: 4
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.9757	0.97	1000	3.3365	126.4090
3.4153	1.94	2000	2.9701	105.5855
2.9747	2.9	3000	2.8029	99.2086
2.6552	3.87	4000	2.6929	102.4891
1.9795	4.84	5000	2.7744	104.8263

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3