README.md

metadata

license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - common_voice_9_0
metrics:
  - wer
model-index:
  - name: cv9-special-batch12-base
    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: 23.92914653784219

cv9-special-batch12-base

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

• Loss: 0.4240
• Wer: 23.9291

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: 12
• eval_batch_size: 6
• 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
0.3536	1.45	1000	0.4083	26.1882
0.2171	2.9	2000	0.3794	24.4813
0.0604	4.35	3000	0.3954	24.5595
0.0531	5.81	4000	0.4079	23.7727
0.0245	7.26	5000	0.4240	23.9291

Framework versions

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