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.
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
Size | Language Code | Model (Download Link) |
---|---|---|
600M | multi | Download |
Models can be downloaded from Huggingface or using the links below.
Language | Language Code | Model (Download Link) |
---|---|---|
Assamese | as | Download |
Bengali | bn | Download |
Bodo | brx | Download |
Dogri | doi | Download |
Gujarati | gu | Download |
Hindi | hi | Download |
Kannada | kn | Download |
Konkani | kok | Download |
Kashmiri | ks | Download |
Maithili | mai | Download |
Malayalam | ml | Download |
Manipuri | mni | Download |
Marathi | mr | Download |
Nepali | ne | Download |
Odia | or | Download |
Punjabi | pa | Download |
Sanskrit | sa | Download |
Santali | sat | Download |
Sindhi | sd | Download |
Tamil | ta | Download |
Telugu | te | Download |
Urdu | ur | Download |
You can also find the Colab notebook here.
IndicConformer is released under the MIT license.