metadata

base_model: openai/whisper-small
datasets:
  - mozilla-foundation/common_voice_11_0
language:
  - id
library_name: transformers
license: apache-2.0
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: whisper-small-id
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: id
          split: None
          args: 'config: id, split: test'
        metrics:
          - type: wer
            value: 16.86124936043537
            name: Wer

whisper-small-id

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

Loss: 0.3366
Wer: 16.8612

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: 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
0.1798	1.9305	1000	0.2465	17.3310
0.0379	3.8610	2000	0.2716	17.6985
0.0058	5.7915	3000	0.3082	17.6334
0.0017	7.7220	4000	0.3317	16.7822
0.0013	9.6525	5000	0.3366	16.8612

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 3.0.0
Tokenizers 0.19.1