Hugging Face's logo

Spaces:
MihirRPatil
/
ASR
Sleeping

App Files Community
ASR / models /processor_dir /tokenizer_config.json
MihirRPatil's picture
MihirRPatil
deploy: CDAC ASR backend with pitch/stress fix and LLM feedback
88a679b
Raw
History Blame Contribute Delete
8.7 kB
{
 "added_tokens_decoder": {
 "0": {
 "content": "<pad>",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "1": {
 "content": "<unk>",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "3": {
 "content": "aj",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "4": {
 "content": "aw",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "6": {
 "content": "bʲ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "8": {
 "content": "cʷ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "9": {
 "content": "dʒ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "10": {
 "content": "d̪",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "11": {
 "content": "eː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "13": {
 "content": "fʲ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "16": {
 "content": "iː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "19": {
 "content": "kʷ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "22": {
 "content": "mʲ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "24": {
 "content": "oː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "26": {
 "content": "pʲ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "28": {
 "content": "tʃ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "29": {
 "content": "t̪",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "31": {
 "content": "ç",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "32": {
 "content": "ŋ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "33": {
 "content": "ɡ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "34": {
 "content": "ɡʷ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "35": {
 "content": "ɪ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "36": {
 "content": "ɲ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "37": {
 "content": "ɹ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "38": {
 "content": "ɾ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "39": {
 "content": "ɜ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "40": {
 "content": "ɜː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "41": {
 "content": "ɟ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "42": {
 "content": "ɟʷ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "43": {
 "content": "ɖ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "44": {
 "content": "ɑ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "45": {
 "content": "ɑː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "46": {
 "content": "ɒ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "47": {
 "content": "ɒː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "48": {
 "content": "ɔj",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "49": {
 "content": "ɛ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "50": {
 "content": "ɛː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "51": {
 "content": "ə",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "52": {
 "content": "ʊ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "53": {
 "content": "ʎ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "54": {
 "content": "ʃ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "55": {
 "content": "ʈ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "56": {
 "content": "ʈʲ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "57": {
 "content": "ʈʷ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "58": {
 "content": "ʒ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "59": {
 "content": "ʉ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "60": {
 "content": "ʉː",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "61": {
 "content": "ʋ",
 "lstrip": true,
 "normalized": false,
 "rstrip": true,
 "single_word": false,
 "special": false
 },
 "62": {
 "content": "<s>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "63": {
 "content": "</s>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 }
 },
 "bos_token": "<s>",
 "clean_up_tokenization_spaces": false,
 "do_lower_case": false,
 "eos_token": "</s>",
 "extra_special_tokens": {},
 "model_max_length": 1000000000000000019884624838656,
 "pad_token": "<pad>",
 "processor_class": "Wav2Vec2Processor",
 "replace_word_delimiter_char": " ",
 "target_lang": null,
 "tokenizer_class": "Wav2Vec2CTCTokenizer",
 "unk_token": "<unk>",
 "word_delimiter_token": "|"
}