Upload processor

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
 base_model: TifinLab/mms-berber
+library_name: transformers
 tags:
 - generated_from_trainer
 model-index:

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 42,
+  "<s>": 41
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "39": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "ber",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,45 @@
+{
+  "ber": {
+    "-": 1,
+    "[PAD]": 40,
+    "[UNK]": 39,
+    "a": 2,
+    "b": 3,
+    "c": 4,
+    "d": 5,
+    "e": 6,
+    "f": 7,
+    "g": 8,
+    "h": 9,
+    "i": 10,
+    "j": 11,
+    "k": 12,
+    "l": 13,
+    "m": 14,
+    "n": 15,
+    "o": 16,
+    "p": 17,
+    "q": 18,
+    "r": 19,
+    "s": 20,
+    "t": 21,
+    "u": 22,
+    "v": 23,
+    "w": 24,
+    "x": 25,
+    "y": 26,
+    "z": 27,
+    "|": 0,
+    "č": 28,
+    "ǧ": 29,
+    "ɛ": 30,
+    "ɣ": 31,
+    "̣": 32,
+    "ḍ": 33,
+    "ḥ": 34,
+    "ṛ": 35,
+    "ṣ": 36,
+    "ṭ": 37,
+    "ẓ": 38
+  }
+}