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_sft_de
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[:10000]
args: 'config: german, split: test'
metrics:
- name: Wer
type: wer
value: 28.608091133538355
whisper_sft_de
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: 0.1840
- Wer: 28.6081
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2232 | 0.08 | 1000 | 0.2541 | 70.0448 |
| 0.2266 | 0.16 | 2000 | 0.2393 | 40.9830 |
| 0.22 | 0.24 | 3000 | 0.2278 | 42.1428 |
| 0.2105 | 0.32 | 4000 | 0.2184 | 41.9078 |
| 0.2108 | 0.4 | 5000 | 0.2090 | 38.9711 |
| 0.1869 | 0.48 | 6000 | 0.2034 | 28.8377 |
| 0.161 | 0.56 | 7000 | 0.1974 | 25.5598 |
| 0.1667 | 0.64 | 8000 | 0.1911 | 27.8122 |
| 0.1891 | 0.72 | 9000 | 0.1860 | 28.4944 |
| 0.1917 | 0.8 | 10000 | 0.1840 | 28.6081 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3