README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - deepinfinityai/30_NLEM_Aug_audios_dataset
metrics:
  - wer
model-index:
  - name: v04_30_NLEM_Aug_Tablets_Model
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: /30_NLEM_Aug_audios_dataset
          type: deepinfinityai/30_NLEM_Aug_audios_dataset
        metrics:
          - name: Wer
            type: wer
            value: 0

v04_30_NLEM_Aug_Tablets_Model

This model is a fine-tuned version of openai/whisper-medium on the /30_NLEM_Aug_audios_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001
• Wer: 0.0

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 218
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.7877	1.0	44	7.8985	100.0
0.1978	2.0	88	0.0365	5.7143
0.0026	3.0	132	0.0002	0.0
0.0001	4.0	176	0.0001	0.0

Framework versions

• Transformers 4.50.3
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0