README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - Dev372/Medical_STT_Dataset_1.1
metrics:
  - wer
model-index:
  - name: OutcomesAI-Whisper-tiny-v1.0
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Medical_STT_Dataset_1.1
          type: Dev372/Medical_STT_Dataset_1.1
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 7.224272510532676

OutcomesAI-Whisper-tiny-v1.0

This model is a fine-tuned version of openai/whisper-tiny on the Medical_STT_Dataset_1.1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1675
• Wer: 7.2243

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: 16
• eval_batch_size: 8
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1067	2.5126	1000	0.1600	7.2308
0.0329	5.0251	2000	0.1479	6.5809
0.0131	7.5377	3000	0.1596	7.4104
0.0192	10.0503	4000	0.1675	7.2243

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1