metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: openai/whisper-medium
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: kk
          split: test
          args: kk
        metrics:
          - name: Wer
            type: wer
            value: 36.12903225806451

openai/whisper-medium

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

Loss: 0.6413
Wer: 36.1290

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 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
0.0064	15.011	1000	0.5457	39.7097
0.0009	31.0094	2000	0.5771	38.3548
0.0	47.0078	3000	0.6180	36.4194
0.0	63.0062	4000	0.6349	36.0645
0.0	79.0046	5000	0.6413	36.1290

Framework versions

Transformers 4.46.0.dev0
Pytorch 2.5.0+cu118
Datasets 3.0.3.dev0
Tokenizers 0.20.1