README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - ami
metrics:
  - wer
model-index:
  - name: model_optimization
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ami
          type: ami
          config: ihm
          split: None
          args: ihm
        metrics:
          - name: Wer
            type: wer
            value: 0.24598930481283424

model_optimization

This model was trained from scratch on the ami dataset. It achieves the following results on the evaluation set:

• Loss: 2.0220
• Wer: 0.2460

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: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2804	50.0	250	1.8094	0.3636
0.637	100.0	500	2.6436	0.3155
0.4223	150.0	750	1.6623	0.2406
0.3273	200.0	1000	2.0220	0.2460

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1