---
license: apache-2.0
language:
- de
library_name: transformers
pipeline_tag: automatic-speech-recognition
---

# whisper-tiny-german

This model is a German Speech Recognition model based on the [whisper-tiny](https://huggingface.co/openai/whisper-tiny) model.
The model weights count 37.8M parameters and with a size of 73MB in bfloat16 format.

As a follow-up to the [Whisper large v3 german](https://huggingface.co/primeline/whisper-large-v3-german) we decided to create a tiny version to be used in edge cases where the model size is a concern.

## Intended uses & limitations

The model is intended to be used for German speech recognition tasks.
It is designed to be used for edge cases where the model size is a concern.
It's not recommended to use this model for critical use cases, as it is a tiny model and may not perform well in all scenarios.

## Dataset

The dataset used for training is a filtered subset of the [Common Voice](https://huggingface.co/datasets/common_voice) dataset, multilingual librispeech and some internal data.
The data was filtered and double checked for quality and correctness.
We did some normalization to the text data, especially for casing and punctuation.


## Model family

| Model  	| Parameters  	| link  	|
|---	|---	|---	|---	|---	|
| Whisper large v3 german  	| 1.54B  	| [link](https://huggingface.co/primeline/whisper-large-v3-german) 	|
| Distil-whisper large v3 german  	| 756M  	|   	|
| tiny whisper  	| 37.8M  	|   	|

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-05
- total_train_batch_size: 512
- num_epochs: 5.0

### Framework versions

- Transformers 4.39.3
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.18.0
- Tokenizers 0.15.2