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
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.
IndicConformer is released under the MIT license.