metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: openai/whisper-small
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: eu
          split: test
          args: eu
        metrics:
          - name: Wer
            type: wer
            value: 11.838103265051853

openai/whisper-small

This model is a fine-tuned version of openai/whisper-small on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.1845
Wer: 11.8381

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: 32
eval_batch_size: 16
seed: 42
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: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2458	1.0296	1000	0.2480	18.0723
0.1099	2.0592	2000	0.1976	13.6355
0.0403	3.0888	3000	0.2002	12.7249
0.0211	4.1184	4000	0.2101	12.4327
0.0609	5.148	5000	0.1845	11.8381

Framework versions

Transformers 4.46.0.dev0
Pytorch 2.4.1+cu121
Datasets 3.0.2.dev0
Tokenizers 0.20.0