metadata

license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - wer
model-index:
  - name: training
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: test
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 24.53398954167948

training

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

Loss: 0.3025
Wer: 24.5340

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
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
0.3282	0.81	1000	0.3106	42.8176
0.1619	1.62	2000	0.2932	27.0624
0.0531	2.43	3000	0.2985	25.3645
0.0208	3.24	4000	0.3025	24.5340

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.2.1+cu118
Datasets 2.17.1
Tokenizers 0.15.2