metadata
language:
- de
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0,facebook/voxpopuli,google/fleurs
metrics:
- wer
model-index:
- name: Whisper LargeV2 German
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: >-
mozilla-foundation/common_voice_11_0,facebook/voxpopuli,google/fleurs
de,de,de_de
type: >-
mozilla-foundation/common_voice_11_0,facebook/voxpopuli,google/fleurs
config: de
split: test
args: de
metrics:
- name: Wer
type: wer
value: 6.313937972585015
Whisper LargeV2 German
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0,facebook/voxpopuli,google/fleurs de,de,de_de dataset. It achieves the following results on the evaluation set:
- Loss: 0.1307
- Wer: 6.3139
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: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.127 | 0.17 | 500 | 0.1569 | 7.2588 |
| 0.1116 | 0.33 | 1000 | 0.1505 | 7.2372 |
| 0.1132 | 0.5 | 1500 | 0.1435 | 6.8821 |
| 0.0939 | 0.67 | 2000 | 0.1354 | 6.5343 |
| 0.0819 | 0.83 | 2500 | 0.1339 | 6.4979 |
| 0.0892 | 1.0 | 3000 | 0.1307 | 6.3139 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2