|
--- |
|
language: |
|
- de |
|
license: apache-2.0 |
|
tags: |
|
- sbb-asr |
|
- generated_from_trainer |
|
datasets: |
|
- marccgrau/sbbdata_allSNR |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Large-v2 German SBB ASR |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: SBB Dataset 05.01.2023 |
|
type: marccgrau/sbbdata_allSNR |
|
args: 'config: German, split: train, test, val' |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.020291693088142042 |
|
--- |
|
|
|
<!-- 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 Large-v2 German SBB ASR |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the SBB Dataset 05.01.2023 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0272 |
|
- Wer: 0.0203 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 600 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 1.3449 | 0.36 | 100 | 0.2160 | 0.0387 | |
|
| 0.0651 | 0.71 | 200 | 0.0278 | 0.0184 | |
|
| 0.0312 | 1.07 | 300 | 0.0316 | 0.0228 | |
|
| 0.019 | 1.42 | 400 | 0.0259 | 0.0209 | |
|
| 0.0135 | 1.78 | 500 | 0.0301 | 0.0203 | |
|
| 0.0091 | 2.14 | 600 | 0.0272 | 0.0203 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.12.1 |
|
|
