indicconformer-600m-onnx / language_spans.json
christopherthompson81's picture
Initial upload: repackaged IndicConformer 600M ONNX
aa6c4d4 verified
{
"total_vocab_size": 5632,
"blank_token_id": 5632,
"languages": {
"as": {
"start": 0,
"length": 256
},
"bn": {
"start": 256,
"length": 256
},
"brx": {
"start": 512,
"length": 256
},
"doi": {
"start": 768,
"length": 256
},
"kok": {
"start": 1024,
"length": 256
},
"gu": {
"start": 1280,
"length": 256
},
"hi": {
"start": 1536,
"length": 256
},
"kn": {
"start": 1792,
"length": 256
},
"ks": {
"start": 2048,
"length": 256
},
"mai": {
"start": 2304,
"length": 256
},
"ml": {
"start": 2560,
"length": 256
},
"mr": {
"start": 2816,
"length": 256
},
"mni": {
"start": 3072,
"length": 256
},
"ne": {
"start": 3328,
"length": 256
},
"or": {
"start": 3584,
"length": 256
},
"pa": {
"start": 3840,
"length": 256
},
"sa": {
"start": 4096,
"length": 256
},
"sat": {
"start": 4352,
"length": 256
},
"sd": {
"start": 4608,
"length": 256
},
"ta": {
"start": 4864,
"length": 256
},
"te": {
"start": 5120,
"length": 256
},
"ur": {
"start": 5376,
"length": 256
}
}
}