Whisper Large V3 German

🚀 Whisper Large v3 German Model

This model is based on Whisper Large v3 and fine - tuned for German speech recognition, offering high - quality performance in various German - related speech applications.

🚀 Quick Start

The following is a Python code example demonstrating how to use this model for automatic speech recognition:

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-large-v3-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"])

✨ Features

• High - performance German Speech Recognition: Optimized for German speech, it can accurately transcribe spoken German.
• Versatile Applications: Can be used in transcription, voice commands, automatic subtitling, voice - based search, and dictation functions.

📚 Documentation

Summary

This model map provides information about a model based on Whisper Large v3 that has been fine - tuned for speech recognition in German. Whisper is a powerful speech recognition platform developed by OpenAI. This model has been specially optimized for processing and recognizing German speech.

Applications

This model can be used in various application areas, including:

• Transcription of spoken German language
• Voice commands and voice control
• Automatic subtitling for German videos
• Voice - based search queries in German
• Dictation functions in word processing programs

Model family

Training data

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.

Training process

The training of the model was performed with the following hyperparameters:

• Batch size: 1024
• Epochs: 2
• Learning rate: 1e - 5
• Data augmentation: No

🔧 Technical Details

The model, named "whisper - large - v3 - german by Florian Zimmermeister @primeLine", is fine - tuned for German speech recognition. The evaluation results on the Common Voice de dataset show a Test WER of 3.002% and a Test CER of 0.81%. There is also a new version named primeline/whisper - large - v3 - turbo - german.

📄 License

This model is released under the Apache 2.0 license.

About us

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

⚠️ Important Note

This model is not a product of the primeLine Group. It represents research conducted by Florian Zimmermeister, 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.