---
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       | [link](https://huggingface.co/primeline/distil-whisper-large-v3-german) |
| tiny whisper                     | 37.8M      | [link](https://huggingface.co/primeline/whisper-tiny-german) |

### 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


### How to use

```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "primeline/whisper-tiny-german"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
```


## [About us](https://primeline-ai.com/en/)

[![primeline AI](https://primeline-ai.com/wp-content/uploads/2024/02/pl_ai_bildwortmarke_original.svg)](https://primeline-ai.com/en/)


Your partner for AI infrastructure in Germany <br>
Experience the powerful AI infrastructure that drives your ambitions in Deep Learning, Machine Learning & High-Performance Computing. Optimized for AI training and inference.



Model author: [Florian Zimmermeister](https://huggingface.co/flozi00)