Update standalone weights with full 625-step fine-tuning (1 complete epoch)

config.json

@@ -30,7 +30,6 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 32,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,

generation_config.json

@@ -32,7 +32,16 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -142,7 +151,96 @@
   "pad_token_id": 50257,
   "prev_sot_token_id": 50362,
   "return_timestamps": false,
-  "suppress_tokens": [],
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
   "task_to_id": {
     "transcribe": 50360,
     "translate": 50359

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626eceabd3f43929fbd8b92dddc14b7bf316754b38c89ac1b553c65d0b7108a5
+oid sha256:746bc61e82a54f31f5d0e5cbec9787806828de142378ea7f86219bf88e87481f
 size 1617824864

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 448,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -14506,6 +14501,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "<|hi|>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<|transcribe|>",
@@ -14538,6 +14539,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "<|hi|>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<|transcribe|>",
@@ -14579,6 +14586,15 @@
           "<|endoftext|>"
         ]
       },
+      "<|hi|>": {
+        "id": "<|hi|>",
+        "ids": [
+          50276
+        ],
+        "tokens": [
+          "<|hi|>"
+        ]
+      },
       "<|notimestamps|>": {
         "id": "<|notimestamps|>",
         "ids": [

tokenizer_config.json

@@ -115,7 +115,7 @@
     "<|notimestamps|>"
   ],
   "is_local": false,
-  "language": null,
+  "language": "hindi",
   "local_files_only": false,
   "max_length": 448,
   "model_max_length": 1000000000000000019884624838656,