preprocessor_config.json
| 1 | { |
| 2 | "feature_extractor_type": "SeamlessM4TFeatureExtractor", |
| 3 | "feature_size": 80, |
| 4 | "language_code": [ |
| 5 | "__afr__", |
| 6 | "__amh__", |
| 7 | "__arb__", |
| 8 | "__ary__", |
| 9 | "__arz__", |
| 10 | "__asm__", |
| 11 | "__azj__", |
| 12 | "__bel__", |
| 13 | "__ben__", |
| 14 | "__bos__", |
| 15 | "__bul__", |
| 16 | "__cat__", |
| 17 | "__ceb__", |
| 18 | "__ces__", |
| 19 | "__ckb__", |
| 20 | "__cmn__", |
| 21 | "__cmn_Hant__", |
| 22 | "__cym__", |
| 23 | "__dan__", |
| 24 | "__deu__", |
| 25 | "__ell__", |
| 26 | "__eng__", |
| 27 | "__est__", |
| 28 | "__eus__", |
| 29 | "__fin__", |
| 30 | "__fra__", |
| 31 | "__fuv__", |
| 32 | "__gaz__", |
| 33 | "__gle__", |
| 34 | "__glg__", |
| 35 | "__guj__", |
| 36 | "__heb__", |
| 37 | "__hin__", |
| 38 | "__hrv__", |
| 39 | "__hun__", |
| 40 | "__hye__", |
| 41 | "__ibo__", |
| 42 | "__ind__", |
| 43 | "__isl__", |
| 44 | "__ita__", |
| 45 | "__jav__", |
| 46 | "__jpn__", |
| 47 | "__kan__", |
| 48 | "__kat__", |
| 49 | "__kaz__", |
| 50 | "__khk__", |
| 51 | "__khm__", |
| 52 | "__kir__", |
| 53 | "__kor__", |
| 54 | "__lao__", |
| 55 | "__lit__", |
| 56 | "__lug__", |
| 57 | "__luo__", |
| 58 | "__lvs__", |
| 59 | "__mai__", |
| 60 | "__mal__", |
| 61 | "__mar__", |
| 62 | "__mkd__", |
| 63 | "__mlt__", |
| 64 | "__mni__", |
| 65 | "__mya__", |
| 66 | "__nld__", |
| 67 | "__nno__", |
| 68 | "__nob__", |
| 69 | "__npi__", |
| 70 | "__nya__", |
| 71 | "__ory__", |
| 72 | "__pan__", |
| 73 | "__pbt__", |
| 74 | "__pes__", |
| 75 | "__pol__", |
| 76 | "__por__", |
| 77 | "__ron__", |
| 78 | "__rus__", |
| 79 | "__sat__", |
| 80 | "__slk__", |
| 81 | "__slv__", |
| 82 | "__sna__", |
| 83 | "__snd__", |
| 84 | "__som__", |
| 85 | "__spa__", |
| 86 | "__srp__", |
| 87 | "__swe__", |
| 88 | "__swh__", |
| 89 | "__tam__", |
| 90 | "__tel__", |
| 91 | "__tgk__", |
| 92 | "__tgl__", |
| 93 | "__tha__", |
| 94 | "__tur__", |
| 95 | "__ukr__", |
| 96 | "__urd__", |
| 97 | "__uzn__", |
| 98 | "__vie__", |
| 99 | "__yor__", |
| 100 | "__yue__", |
| 101 | "__zlm__", |
| 102 | "__zul__" |
| 103 | ], |
| 104 | "num_mel_bins": 80, |
| 105 | "padding_side": "right", |
| 106 | "padding_value": 0.0, |
| 107 | "processor_class": "SeamlessM4TProcessor", |
| 108 | "return_attention_mask": true, |
| 109 | "sampling_rate": 16000, |
| 110 | "stride": 2 |
| 111 | } |
| 112 | |