About this Maithili Automatic Speech Recognition System

The tool “(Maithili-ASR)” is an outcome of the PhD research work submitted in the year 2024 on the topic “Automatic Speech Recognition in Maithili: Issues & Challenges” conducted by Mr. Shantanu Kumar under the supervision of Dr Narayan Choudhary at the Central Institute of Indian Languages & University of Mysore. This tool has been developed with the technical support of domain-specific experts Mr Stephen Fernandes and Mr Writtik Bhattacharya.

The primary function of this tool is to provide the transcription of Maithili audio in the Devanagari Script. The tool accepts raw audio as an input and provides the corresponding text as an output. This tool can transcribe any live audio and/or pre-recorded audio files. This tool can transcribe audio sound files in any format (mp3/wav/any other) with a maximum file size of 100 mb.

To utilize this tool, please click on the mic button, record your voice spoken in Maithili, click the stop button, and get the transcription of your speech in the text box area.

Also, to get the transcription of any pre-recorded speech, please click on the browse file button, select the audio file, click on the transcribe button, and get the corresponding transcription in the text box area.

Limitations of the Demo Tool

The tool hosted on a system with limited resources. Therefore, it is taking an audio input file of only upto 50MB

Please do not record more than 1 minute of audio in one go as the size may increase to 50MB.

The tool does take into account punctuations and punctuation marks are not recognized. So, please do not treat it as an optimized dictation tool

Disclaimer/Notice

We keep a record the speech being recorded on this system. By using this tool, you agree to give your consent to keep the audio uploaded or recorded by you. We may not know your name and other personal details, but your voice will remain with us for further research and development.