GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
primeline
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
primeline
Model Tree
Base
primeline/whisper-large-v3-german
Fine-tuned
this model
Input Modalities
Audio
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
| Model | Parameters | link |
|---|---|---|
| Whisper large v3 german | 1.54B | link |
| Whisper large v3 turbo german | 809M | link |
| Distil-whisper large v3 german | 756M | link |
| tiny whisper | 37.8M | link |
| Dataset | openai-whisper-large-v3-turbo | openai-whisper-large-v3 | primeline-whisper-large-v3-german | nyrahealth-CrisperWhisper (large) | primeline-whisper-large-v3-turbo-german |
|---|---|---|---|---|---|
| Tuda-De | 8.300 | 7.884 | 7.711 | 5.148 | 6.441 |
| common_voice_19_0 | 3.849 | 3.484 | 3.215 | 1.927 | 3.200 |
The data and code for evaluations are available here
The training data for this model includes a large amount of spoken German from various sources. The data was carefully selected and processed to optimize recognition performance.
The training of the model was performed with the following hyperparameters
python
import torchfrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipelinefrom datasets import load_datasetdevice = "cuda:0" if torch.cuda.is_available() else "cpu"torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32model_id = "primeline/whisper-large-v3-turbo-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"])
Your partner for AI infrastructure in Germany
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
Disclaimer
markdown
This model is not a product of the primeLine Group.It represents research conducted by [Florian Zimmermeister](https://huggingface.co/flozi00), with computing power sponsored by primeLine.The model is published under this account by primeLine, but it is not a commercial product of primeLine Solutions GmbH.Please be aware that while we have tested and developed this model to the best of our abilities, errors may still occur.Use of this model is at your own risk. We do not accept liability for any incorrect outputs generated by this model.
| multilingual librispeech |
| 3.203 |
| 2.832 |
| 2.129 |
| 2.815 |
| 2.070 |
| All | 3.649 | 3.279 | 2.734 | 2.662 | 2.628 |