metadata
library_name: transformers
language:
- uk
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Medium uk - Herai Hench KI-11
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: uk
split: None
args: 'config: uk, split: test'
metrics:
- name: Wer
type: wer
value: 28.720238095238095
Whisper Medium uk - Herai Hench KI-11
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2959
- Wer: 28.7202
- Cer: 7.4673
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: 6e-06
- 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: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.2705 | 0.6048 | 750 | 0.3558 | 33.9286 | 9.0582 |
| 0.1533 | 1.2097 | 1500 | 0.2959 | 28.7202 | 7.4673 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0