metadata

license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
datasets:
  - impaired_v3_independent_all
metrics:
  - wer
model-index:
  - name: impaired-v3-independent-all
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: impaired_v3_independent_all
          type: impaired_v3_independent_all
          config: cs
          split: test
          args: cs
        metrics:
          - name: Wer
            type: wer
            value: 0.4068825910931174

impaired-v3-independent-all

This model is a fine-tuned version of openai/whisper-large-v3 on the impaired_v3_independent_all dataset. It achieves the following results on the evaluation set:

Loss: 1.4531
Wer: 0.4069

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: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0077	13.99	1000	1.0277	0.3968
0.0008	27.97	2000	1.2058	0.4008
0.0001	41.96	3000	1.3848	0.4069
0.0001	55.94	4000	1.4363	0.3998
0.0001	69.93	5000	1.4531	0.4069

Framework versions

Transformers 4.37.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.1