metadata

library_name: transformers
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - MatthiasZ/whisper_large_v3_turbo_annota_2
metrics:
  - wer
model-index:
  - name: whisper_large_v3_turbo_annota_2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: whisper_large_v3_turbo_annota_2
          type: MatthiasZ/whisper_large_v3_turbo_annota_2
          args: 'config: de, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 21.886674395921897

whisper_large_v3_turbo_annota_2

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the whisper_large_v3_turbo_annota_2 dataset. It achieves the following results on the evaluation set:

Loss: 0.3910
Wer: 21.8867

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: 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: 500
training_steps: 6000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4409	0.3333	2000	0.4489	23.5761
0.4317	0.6667	4000	0.4141	22.9669
0.3881	1.0	6000	0.3910	21.8867

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3