初始化项目，由ModelHub XC社区提供模型

Model: nikitastheo/phonebabylm-phone-deu-eng-interleaved Source: Original Platform
2026-08-21 19:40:16 +08:00
commit 5cdf22bdab
11 changed files with 566 additions and 0 deletions
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,188 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "UNK",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "PAD",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "UTT_BOUNDARY",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ː"
+        },
+        "content": " ː "
+      },
+      {
+        "type": "Strip",
+        "strip_left": true,
+        "strip_right": true
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "UTT_BOUNDARY",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "UTT_BOUNDARY": {
+        "id": "UTT_BOUNDARY",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "UTT_BOUNDARY"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "UNK": 0,
+      "PAD": 1,
+      "UTT_BOUNDARY": 2,
+      "ɪ": 3,
+      "ç": 4,
+      "WORD_BOUNDARY": 5,
+      "v": 6,
+      "a": 7,
+      "ː": 8,
+      "ɐ": 9,
+      "aʊ": 10,
+      "f": 11,
+      "ʀ": 12,
+      "aɪ": 13,
+      "z": 14,
+      "ə": 15,
+      "n": 16,
+      "ʊ": 17,
+      "t": 18,
+      "h": 19,
+      "ts": 20,
+      "m": 21,
+      "b": 22,
+      "ɡ": 23,
+      "ɔ": 24,
+      "d": 25,
+      "s": 26,
+      "ʃ": 27,
+      "i": 28,
+      "ʊɐ": 29,
+      "l": 30,
+      "ŋ": 31,
+      "ɛ": 32,
+      "e": 33,
+      "u": 34,
+      "k": 35,
+      "ʏ": 36,
+      "j": 37,
+      "p": 38,
+      "x": 39,
+      "o": 40,
+      "y": 41,
+      "œ": 42,
+      "pf": 43,
+      "ø": 44,
+      "w": 45,
+      "eɪ": 46,
+      "ɒ": 47,
+      "t̠ʃ": 48,
+      "d̠ʒ": 49,
+      "ã": 50,
+      "əʊ": 51,
+      "ɹ": 52,
+      "eə": 53,
+      "ʌ": 54,
+      "ɛɪ": 55,
+      "ð": 56,
+      "ɔɪ": 57,
+      "ʒ": 58,
+      "iə": 59,
+      "θ": 60,
+      "ʊə": 61,
+      "œ̃": 62,
+      "ɔ̃": 63,
+      "l̩": 64,
+      "tɕ": 65,
+      "ɕ": 66,
+      "c": 67,
+      "ɲ": 68,
+      "tʰ": 69,
+      "æ": 70,
+      "ɜ": 71,
+      "ɑ": 72,
+      "oʊ": 73,
+      "ʂ": 74,
+      "ʈ": 75,
+      "ɖ": 76,
+      "ɭ": 77,
+      "ʋ": 78,
+      "ʰχ": 79,
+      "ʲ": 80,
+      "ɟ": 81,
+      "ɳ": 82,
+      "bʰ": 83,
+      "dʰ": 84
+    },
+    "unk_token": "UNK"
+  }
+}