About LuxASR
With this interface, we are giving access to our most performant tool for automatic speech recognition of Luxembourgish (speech-to-text). It has been trained on 150+ hours of carefully controlled pairs of audio and transcription snippets and is achieving a word error rate below 10%, i.e. 10 errors per 100 running words (punctuation and case included 😛). We are providing this tool to facilitate the transcription of Luxembourgish audio recordings into written text for research purposes, but also for general public use. The resulting text follows the current spelling rules of 2019.
Available options
Several audio input languages are available (default: Luxembourgish). If the recording contains more than one speaker, setting diarization to ‚On‘ will separate the text of every speaker in the recording along with time codes for their turns. Note that diarization adds some extra time to the recognition process. Four output formats are available: plain text (txt), colored text with confidence scores, SubRip Subtitles (srt), JSON (with time codes and confidence scores for words), Praat TextGrid and BAS WebServices TextGrid. These files can be downloaded through the link below the transcription or shared via the share button. The recognition duration takes up to 5% of the audio file’s duration. Once the recognition process has started, an estimated time and a timer will be displayed to keep track of the progress.
As an experimental feature for the text translation to other languages has been added, which will output the recognized text in English, German, Portuguese, Spanish or French. Note that translations take more time to run and will run only for short audios. The quality of these translations may vary.
The maximal size for upload is 500 MB. The preferred file format for audio files is ‚wav‘ with a sampling frequency of 16,000 Hz. Other formats are also supported (mp3, m4a, mp4 etc). Note that depending on the file type and file size, the recognition process may take longer.
Note that for the new BAS TextGrid option, the audio and text are sent to the BAS services. Please review their privacy statement for more information.
API Access
We are opening API access now. The LuxASR API can be reached via:
curl -X POST "https://luxasr.uni.lu/v2/asr?diarization=Enabled&outfmt=text" \
-H "accept: application/json" \
-F "audio_file=@PATH/TO/AUDIO FILE;type=audio/wav"
The API returns the transcription in the specified output format.
Query Parameters
- diarization: Can be set to
Enabled
(default) or Disabled
to include or exclude speaker diarization.
- outfmt: Specifies the output format. Supported values are:
text
– plain text transcript (default)
json
– detailed JSON output
srt
– SubRip subtitle format
textgrid
– Praat TextGrid format
bas_textgrid
– BAS WebServices TextGrid format (experimental)
Accepted audio formats are .wav, .mp3, and .m4a.
Note that for the BAS TextGrid option, the audio and text are sent to the BAS services. Please review their privacy statement for more information.
Python Script
Below is a basic Python script that replicates the functionality of the curl
command
with added flexibility. You can specify the audio file and optionally choose whether to enable diarization and which output format to use.
Download the Python script to use the LuxASR API.
API Documentation
View the API Documentation for detailed information about the LuxASR API.
Usage
python luxasr_transcribe.py path/to/your_audio.wav --diarization Enabled --outfmt json
Replace path/to/your_audio.wav
with your actual audio file. The --diarization
and --outfmt
options are optional and default to Enabled
and text
respectively.
Disclaimer
Note that the transcription and the translation are run on a dedicated server at the University of Luxembourg. All data thus stays within Luxembourg and the University’s network. Nobody has access to the uploaded audio or the text output. The audio data is streamed to this server and no files are stored on this server or in the network. No data is used to further train the model and no data is transferred to third parties.
Contact
Learn more about LuxASR. LuxASR is under constant development by Peter Gilles, Léopold Hillah, and Nina Hosseini-Kivanani at the University of Luxembourg and is supported by the Chambre des Députes du Grand-Duché de Luxembourg.