metadata
language:
- de
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper small 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: other
args: 'config: de, split: test'
metrics:
- name: Wer
type: wer
value: 11.98839498497565
Whisper small 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: 0.2317
- Wer: 11.9884
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: 7.5e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 220
- training_steps: 2200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2309 | 0.25 | 550 | 0.2681 | 12.4339 |
| 0.1415 | 0.5 | 1100 | 0.2456 | 11.4703 |
| 0.2352 | 0.75 | 1650 | 0.2360 | 11.2216 |
| 0.1589 | 1.0 | 2200 | 0.2317 | 11.9884 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0