update

generation_config.json

@@ -165,7 +165,7 @@
     "<|yue|>": 50358,
     "<|zh|>": 50260
   },
-  "language": "<|en|>",
+  "language": "<|no|>",
   "max_initial_timestamp_index": 1,
   "max_length": 448,
   "no_timestamps_token_id": 50364,

run_distillation_nodes.py

@@ -610,7 +610,7 @@ def get_data_loader(
 
     data_loader = DataLoader(
         dataset,
-        batch_size=batch_sizei //num_of_hosts,
+        batch_size=batch_size //num_of_hosts,
         drop_last=drop_last,
         pin_memory=pin_memory,
         collate_fn=data_collator,

tokenizer.json

@@ -14503,7 +14503,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<|en|>",
+          "id": "<|no|>",
           "type_id": 0
         }
       },
@@ -14541,7 +14541,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<|en|>",
+          "id": "<|no|>",
           "type_id": 0
         }
       },
@@ -14586,22 +14586,22 @@
           "<|endoftext|>"
         ]
       },
-      "<|en|>": {
-        "id": "<|en|>",
+      "<|notimestamps|>": {
+        "id": "<|notimestamps|>",
         "ids": [
-          50259
+          50364
         ],
         "tokens": [
-          "<|en|>"
+          "<|notimestamps|>"
         ]
       },
-      "<|notimestamps|>": {
-        "id": "<|notimestamps|>",
+      "<|no|>": {
+        "id": "<|no|>",
         "ids": [
-          50364
+          50288
         ],
         "tokens": [
-          "<|notimestamps|>"
+          "<|no|>"
         ]
       },
       "<|startoftranscript|>": {