---
language:
- de
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-large-v3
datasets:
- rmacek/ORF-whisper-large-v3
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-large-v3
      args: 'config: de, split: test'
    metrics:
    - type: wer
      value: 17.29558995956067
      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-large-v3](https://huggingface.co./openai/whisper-large-v3) on the ZIB2 Common Voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3878
- Wer: 17.2956

## 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: 16
- 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: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.3943        | 1.7153 | 1000 | 0.4072          | 17.5540 |
| 0.3431        | 3.4305 | 2000 | 0.3922          | 17.3458 |
| 0.3961        | 5.1458 | 3000 | 0.3885          | 17.3506 |
| 0.3548        | 6.8611 | 4000 | 0.3878          | 17.2956 |


### Framework versions

- PEFT 0.10.1.dev0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1