Skip to content

AI4Bharat/IndicConformerASR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

IndicConformer

AI4Bharat's IndicConformers is a suite of ASR models built to deliver accurate speech-to-text conversion in all 22 official Indian languages. By leveraging cutting-edge deep learning techniques, these models provide precise transcriptions. As the country's first open-source ASR system covering such a vast array of languages, AI4Bharat Indic Conformer is a transformative tool for making technology more inclusive and accessible to all.

Usage Instructions

To load, train, fine-tune or play with the model you will need to install AI4Bharat NeMo. We recommend you install it using the command shown below:

git clone https://github.com/AI4Bharat/NeMo.git && cd NeMo && git checkout nemo-v2 && bash reinstall.sh

Resources

Models can be downloaded from Huggingface or using the links below.

Language Code Model (Download Link)
as Download
bn Download
brx Download
doi Download
gu Download
hi Download
kn Download
kok Download
ks Download
mai Download
ml Download
mni Download
mr Download
ne Download
or Download
pa Download
sa Download
sat Download
sd Download
ta Download
te Download
ur Download

You can also find the Colab notebook here.

License

IndicConformer is released under the MIT license.