--- license: cc-by-nc-sa-4.0 language: - lb - de - fr - en - pt tags: - STT - ASR - audio - speech recognition - coqui.ai datasets: - mbarnig/lb-STT-CORPUS --- #### The luxembourgish part of my multilingual automatic speech recognition (ASR) model is the second Machine Learning (ML) STT model for Luxembourgish. The very first model has been published in May 2022 by [Pr Peter Gilles](https://infolux.uni.lu/automatic-speech-recognition-in-luxembourgish-a-very-first-model/) of the University of Luxembourg. #### My model has been trained from scratch with my customized dataset [mbarnig/lb-STT_CORPUS](https://huggingface.co/datasets/mbarnig/lb-STT-CORPUS) and the deep-learning-toolkit ๐Ÿธ [Coqui-STT](https://github.com/coqui-ai/STT) (version 1.3.0). The model was trained without punctuations with the following alphabet: ``` # Each line in this file represents the Unicode codepoint (UTF-8 encoded) # associated with a numeric index. # A line that starts with # is a comment. You can escape it with \# if you wish # to use '#' in the Alphabet. 'abcdefghijklmnopqrstuvwxyz ร รกรขรครงรจรฉรซรฎรดรถรปรผ # The last (non-comment) line needs to end with a newline. ``` #### A live inference-demo of the ASR system is available in my HuggingFace space โŒจ๏ธ ๐Ÿ‡ฑ๐Ÿ‡บ ๐Ÿ”ˆ [mbarnig/lb-de-fr-en-pt-COQUI-STT](https://huggingface.co/spaces/mbarnig/lb-de-fr-en-pt-COQUI-STT). #### Click the tab *training metrics* above to view the live Tensorboard of the model training with the small (2880 samples), with the expanded (27072 samples) dataset, each with and without data augmentation. ![tensorboard](tensorboard/tensorboard-comparison.png)