Model

HTTP 200 OK
Allow: GET, HEAD, OPTIONS
Content-Type: application/json
Vary: Accept

{
    "id": 14,
    "title": "IndicConformer",
    "area": "ASR",
    "published_on": "2024-09-07",
    "conference": null,
    "description": "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. IndicConformer is released under the MIT license.",
    "paper_link": null,
    "colab_link": "https://colab.research.google.com/drive/1ZQJEhYgLKS72_V4LvNmsyU2zF9pICRvE",
    "website_link": "https://ai4bharat.github.io/ai4b-website/areas/model/ASR/IndicConformer",
    "github_link": "https://github.com/AI4Bharat/IndicConformerASR",
    "service_id": "ai4bharat/conformer-multilingual-all--gpu-t4",
    "hf_link": "https://huggingface.co/collections/ai4bharat/indicconformer-66d9e933a243cba4b679cb7f",
    "installation_steps_json": [
        {
            "instruction": "Setting up conda",
            "codeString": null,
            "type": "heading"
        },
        {
            "instruction": "Creating and activating conda environment",
            "codeString": "conda create -n temo python=3.10\nconda activate temo",
            "type": "instruction"
        },
        {
            "instruction": "Installing libraries",
            "codeString": "pip3 install torch torchvision torchaudio\npip install packaging\npip install huggingface_hub==0.23.2",
            "type": "instruction"
        },
        {
            "instruction": "Cloning repository",
            "codeString": "git clone https://github.com/AI4Bharat/NeMo.git\ncd NeMo\nbash reinstall.sh",
            "type": "instruction"
        }
    ],
    "usage_steps_json": [
        {
            "instruction": "Inference",
            "codeString": null,
            "type": "heading"
        },
        {
            "instruction": "Download the model checkpoints from the GitHub repository.",
            "codeString": "https://github.com/AI4Bharat/IndicConformerASR",
            "type": "instruction"
        },
        {
            "instruction": "Loading the checkpoint",
            "codeString": "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nmodel = nemo_asr.models.EncDecCTCModel.restore_from(restore_path='<CHECKPOINT_PATH>.nemo')\nmodel.freeze()\nmodel = model.to(device)",
            "type": "instruction"
        },
        {
            "instruction": "CTC Decoding",
            "codeString": "model.cur_decoder = 'ctc'\nctc_text = model.transcribe(['/path/audio_path.wav'], batch_size=1,logprobs=False, language_id='LANG_ID')[0]",
            "type": "instruction"
        },
        {
            "instruction": "RNN-T Decoding",
            "codeString": "model.cur_decoder = 'rnnt'\nctc_text = model.transcribe(['/path/audio_path.wav'], batch_size=1, language_id='LANG_ID')[0]",
            "type": "instruction"
        }
    ],
    "testimonials_json": null,
    "latest": true,
    "paper_award": null,
    "license": [],
    "type": "Model",
    "hfData": {
        "downloads": 144863
    },
    "services": {
        "ai4bharat/conformer-multilingual-all--gpu-t4": {
            "service_id": "ai4bharat/conformer-multilingual-all--gpu-t4",
            "languageFilters": {
                "sourceLanguages": [
                    "ks",
                    "ne",
                    "kok",
                    "mni",
                    "sd",
                    "bn",
                    "sat",
                    "ml",
                    "mr",
                    "kn",
                    "ta",
                    "sa",
                    "as",
                    "or",
                    "hi",
                    "brx",
                    "te",
                    "gu",
                    "ur",
                    "pa",
                    "doi",
                    "mai"
                ],
                "targetLanguages": []
            }
        }
    }
}