metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-medium.en
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: wme_30s_Static_atMic_1.1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 18.922229026331905

wme_30s_Static_atMic_1.1

This model is a fine-tuned version of openai/whisper-medium.en on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.6879
Wer: 18.9222

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: 4e-05
train_batch_size: 48
eval_batch_size: 32
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: 44
training_steps: 440
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0	0	1.1143	21.3411
0.5297	0.2	88	0.6960	20.5144
0.3945	1.0023	176	0.6817	19.6877
0.1416	1.2023	264	0.6822	19.8408
0.1121	2.0045	352	0.6823	19.2284
0.0366	2.2045	440	0.6879	18.9222

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1