metadata
language:
- de
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: whisper-fine-tuned-de_arg_new
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: de
split: validation[4000:6000]
args: 'config: german, split: test'
metrics:
- name: Wer
type: wer
value: 13.674242424242426
whisper-fine-tuned-de_arg_new
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: 0.3310
- Wer: 13.6742
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.1345 | 1.6 | 1000 | 0.2689 | 13.9665 |
| 0.0125 | 3.2 | 2000 | 0.2994 | 14.0206 |
| 0.0049 | 4.8 | 3000 | 0.3150 | 13.7933 |
| 0.0013 | 6.4 | 4000 | 0.3256 | 13.6526 |
| 0.0009 | 8.0 | 5000 | 0.3310 | 13.6742 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2