unilux/whisper-tiny-v1-luxembourgish

Model Card

🧠 Model Details

• Model name: whisper-tiny-v1-luxembourgish
• Organization: University of Luxembourg — Department of Humanities
• Project: Luxembourgish Automatic Speech Recognition (LuxASR)
• Type: Speech-to-Text (ASR)
• Language: Luxembourgish (lb)
• Architecture: Whisper (Tiny)
• Model size: ~39M parameters
• License: Open Model, Data & Weights (open-mdw)

This model is part of the LuxASR open model family for Luxembourgish speech recognition. Fine-tuned on Luxembourgish audio–text pairs (≈150+ hours total initiative scale).

The tiny, base, small, and medium models are open-sourced; the larger flagship LuxASR model, used in the webservice, the API and the iOS and Android apps, remains closed-source.

---

🚀 Intended Use

• Transcribe Luxembourgish speech into text.
• Research and development of Luxembourgish ASR.
• Accessibility and media transcription.

---

⚙️ Usage Example

from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="unilux/whisper-tiny-v1-luxembourgish")
result = pipe("example.wav")
print(result["text"])

---

🧾 Training Data & Methodology

• Based on OpenAI Whisper architecture.
• Developed by the University of Luxembourg’s LuxASR project.

🧡 Acknowledgements

Developed by the LuxASR team, University of Luxembourg.
See luxasr.uni.lu for project details.

---