metadata

library_name: transformers
language:
  - de
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Large Turbo De - Krish Kalra
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: de
          split: None
          args: 'config: de, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 8.286882199925678

Whisper Large Turbo De - Krish Kalra

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.0916
Wer: 8.2869

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: 5e-06
train_batch_size: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0848	1.0	71	0.1814	12.4423
0.0465	2.0	142	0.1093	5.4150
0.0403	3.0	213	0.0916	8.2869

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3