|
|
--- |
|
|
language: |
|
|
- de |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: openai/whisper-small |
|
|
datasets: |
|
|
- rmacek/ORF-whisper-small |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: Whisper ORF Bundeslaender |
|
|
results: |
|
|
- task: |
|
|
type: automatic-speech-recognition |
|
|
name: Automatic Speech Recognition |
|
|
dataset: |
|
|
name: ZIB2 Common Voice |
|
|
type: rmacek/ORF-whisper-small |
|
|
args: 'config: de, split: test' |
|
|
metrics: |
|
|
- type: wer |
|
|
value: 27.268895060503866 |
|
|
name: Wer |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# Whisper ORF Bundeslaender |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ZIB2 Common Voice dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.7038 |
|
|
- Wer: 27.2689 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- training_steps: 8000 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:-------:| |
|
|
| 0.4896 | 1.7153 | 1000 | 0.6019 | 26.6961 | |
|
|
| 0.3559 | 3.4305 | 2000 | 0.6038 | 26.6192 | |
|
|
| 0.259 | 5.1458 | 3000 | 0.6216 | 33.8450 | |
|
|
| 0.3272 | 6.8611 | 4000 | 0.6382 | 27.0730 | |
|
|
| 0.2413 | 8.5763 | 5000 | 0.6704 | 31.3207 | |
|
|
| 0.1691 | 10.2916 | 6000 | 0.6922 | 27.2466 | |
|
|
| 0.1702 | 12.0069 | 7000 | 0.7008 | 27.3284 | |
|
|
| 0.1726 | 13.7221 | 8000 | 0.7038 | 27.2689 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.10.1.dev0 |
|
|
- Transformers 4.40.0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.19.0 |
|
|
- Tokenizers 0.19.1 |
