Downloads · 30 days
23
9% of all-time downloads
whisper-tiny-german-ct2
pbechhaus/whisper-tiny-german-ct2
whisper-tiny-german-ct2 is a automatic speech recognition model from pbechhaus. Use it when you need speech turned into text. The card lists the license as apache-2.0.
This model is a CTranslate2-optimized version of primeline/whisper-tiny-german, converted for efficient inference with the faster-whisper library.
All-time downloads
249
Public
Repo size
75.5 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin75.5 MB · 96%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Access
- Public
- Created
- Oct 9, 2025
- Updated
- Oct 9, 2025
- SHA
- f78f3efc
Base models
Model card
From the Hugging Face model README
Whisper Tiny German - CTranslate2
This model is a CTranslate2-optimized version of primeline/whisper-tiny-german, converted for efficient inference with the faster-whisper library.
Model Details
- Base Model: primeline/whisper-tiny-german
- Format: CTranslate2 with FP16 quantization
- Language: German (de)
- Model Size: 72 MB
- Architecture: Whisper Tiny (39M parameters)
Performance
Benchmarked on NVIDIA RTX 5090:
- Processing Speed: 46x real-time on average
- Average Latency: 0.108s per audio segment
- WER on FLEURS (de_de): 29.15%
- CER on FLEURS (de_de): 10.11%
- Reliability: 99% of samples processed without issues (9/862 problematic cases)
- Stability: No hallucination patterns detected
Installation
pip install faster-whisper
Acknowledgments
- Original Whisper model by OpenAI
- German fine-tuning by primeline
- CTranslate2 optimization framework by SYSTRAN
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Languages
- de
- Created
- Oct 9, 2025
- Updated
- Oct 9, 2025