Training in progress, step 50

config.json

@@ -27,5 +27,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.48.1",
   "use_cache": true,
-  "vocab_size": 39
+  "vocab_size": 54
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be81500bcad2109a2fd035be669aa8747d61cb916cd1fb73bf942d6a8166962
-size 3415728
+oid sha256:746a8c8ffd22f16480438eebc8301a8321e29b83e3d93a1f9cce810b3c0f781a
+size 3432768

tokenizer.json

@@ -43,6 +43,146 @@
   "normalizer": {
     "type": "Sequence",
     "normalizers": [
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "e-"
+        },
+        "content": "ˈe"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ə-"
+        },
+        "content": "ˈə"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "a-"
+        },
+        "content": "ˈa"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌa"
+        },
+        "content": "ˈa"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌɛ"
+        },
+        "content": "ˈɛ"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌi"
+        },
+        "content": "ˈi"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌɔ"
+        },
+        "content": "ˈɔ"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌɑ̃"
+        },
+        "content": "ˈɑ̃"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˈə-"
+        },
+        "content": "ˈə"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "y-"
+        },
+        "content": "ˈy"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˈe-"
+        },
+        "content": "ˈe"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˈa-"
+        },
+        "content": "ˈa"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌɛ̃"
+        },
+        "content": "ˈɛ̃"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌu"
+        },
+        "content": "ˈu"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌœ"
+        },
+        "content": "ˈœ"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌø"
+        },
+        "content": "ˈø"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌe"
+        },
+        "content": "ˈe"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌə"
+        },
+        "content": "ˈə"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌy"
+        },
+        "content": "ˈy"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ˌo"
+        },
+        "content": "ˈo"
+      },
       {
         "type": "Strip",
         "strip_left": true,
@@ -51,7 +191,7 @@
     ]
   },
   "pre_tokenizer": {
-    "type": "Whitespace"
+    "type": "WhitespaceSplit"
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -117,39 +257,54 @@
       "UTT_BOUNDARY": 3,
       "m": 4,
       "a": 5,
-      "ɑ̃": 6,
+      "ˈɑ̃": 6,
       "d": 7,
-      "ɔ": 8,
+      "ˈɔ": 8,
       "n": 9,
       "b": 10,
-      "ʁ": 11,
-      "ə": 12,
-      "ɡ": 13,
-      "ʒ": 14,
-      "i": 15,
-      "v": 16,
-      "t": 17,
-      "k": 18,
-      "o": 19,
-      "ɛ̃": 20,
-      "w": 21,
-      "y": 22,
-      "j": 23,
-      "e": 24,
-      "ɔ̃": 25,
-      "p": 26,
-      "ɛ": 27,
-      "f": 28,
-      "s": 29,
-      "z": 30,
-      "l": 31,
-      "u": 32,
-      "ʃ": 33,
-      "œ": 34,
-      "ø": 35,
-      "ɲ": 36,
-      "t̠ʃ": 37,
-      "d̠ʒ": 38
+      "ˈa": 11,
+      "ʁ": 12,
+      "ə": 13,
+      "ɡ": 14,
+      "ɔ": 15,
+      "ʒ": 16,
+      "ˈi": 17,
+      "v": 18,
+      "t": 19,
+      "k": 20,
+      "ˈo": 21,
+      "ˈɛ̃": 22,
+      "w": 23,
+      "y": 24,
+      "j": 25,
+      "ˈy": 26,
+      "e": 27,
+      "ɔ̃": 28,
+      "ˈe": 29,
+      "p": 30,
+      "ɛ": 31,
+      "f": 32,
+      "s": 33,
+      "z": 34,
+      "l": 35,
+      "ˈə": 36,
+      "ˈɛ": 37,
+      "u": 38,
+      "o": 39,
+      "ʃ": 40,
+      "i": 41,
+      "ˈu": 42,
+      "ɛ̃": 43,
+      "œ": 44,
+      "ˈø": 45,
+      "ɑ̃": 46,
+      "ˈœ": 47,
+      "ˈɔ̃": 48,
+      "ø": 49,
+      "ɲ": 50,
+      "ˈw": 51,
+      "t̠ʃ": 52,
+      "d̠ʒ": 53
     },
     "unk_token": "UNK"
   }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f638c7b21758ebe8a00a85fa86d18709257799ae97cf8318e82593db8582985
+oid sha256:57ddf9aba19f8626fff58dda625a730f79b2c840806845062dbd8136667c3774
 size 5496

vocab.json

@@ -1 +1 @@
-{"UNK":0,"PAD":1,"WORD_BOUNDARY":2,"UTT_BOUNDARY":3,"m":4,"a":5,"ɑ̃":6,"d":7,"ɔ":8,"n":9,"b":10,"ʁ":11,"ə":12,"ɡ":13,"ʒ":14,"i":15,"v":16,"t":17,"k":18,"o":19,"ɛ̃":20,"w":21,"y":22,"j":23,"e":24,"ɔ̃":25,"p":26,"ɛ":27,"f":28,"s":29,"z":30,"l":31,"u":32,"ʃ":33,"œ":34,"ø":35,"ɲ":36,"t̠ʃ":37,"d̠ʒ":38}
+{"UNK":0,"PAD":1,"WORD_BOUNDARY":2,"UTT_BOUNDARY":3,"m":4,"a":5,"ˈɑ̃":6,"d":7,"ˈɔ":8,"n":9,"b":10,"ˈa":11,"ʁ":12,"ə":13,"ɡ":14,"ɔ":15,"ʒ":16,"ˈi":17,"v":18,"t":19,"k":20,"ˈo":21,"ˈɛ̃":22,"w":23,"y":24,"j":25,"ˈy":26,"e":27,"ɔ̃":28,"ˈe":29,"p":30,"ɛ":31,"f":32,"s":33,"z":34,"l":35,"ˈə":36,"ˈɛ":37,"u":38,"o":39,"ʃ":40,"i":41,"ˈu":42,"ɛ̃":43,"œ":44,"ˈø":45,"ɑ̃":46,"ˈœ":47,"ˈɔ̃":48,"ø":49,"ɲ":50,"ˈw":51,"t̠ʃ":52,"d̠ʒ":53}