Upload processor

README.md

@@ -1,8 +1,8 @@
 ---
 license: cc-by-nc-4.0
-base_model: facebook/mms-1b-all
 tags:
 - generated_from_trainer
+base_model: facebook/mms-1b-all
 metrics:
 - wer
 model-index:

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "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

@@ -39,6 +39,7 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -2,13 +2,13 @@
   "[PAD]": 41,
   "[UNK]": 40,
   "|": 0,
-  "င": 1,
-  "တ": 2,
-  "ထ": 3,
-  "ပ": 4,
-  "မ": 5,
-  "ယ": 6,
-  "ရ": 7,
+  " ": 1,
+  "င": 2,
+  "တ": 3,
+  "ထ": 4,
+  "ပ": 5,
+  "မ": 6,
+  "ယ": 7,
   "လ": 8,
   "ဝ": 9,
   "သ": 10,