Training in progress, step 500

added_tokens.json

@@ -17,7 +17,6 @@
   "<|da|>": 50285,
   "<|de|>": 50261,
   "<|el|>": 50281,
-  "<|endoftext|>": 50257,
   "<|en|>": 50259,
   "<|es|>": 50262,
   "<|et|>": 50307,
@@ -30,6 +29,7 @@
   "<|gu|>": 50333,
   "<|haw|>": 50352,
   "<|ha|>": 50354,
+  "<|he|>": 50279,
   "<|hi|>": 50276,
   "<|hr|>": 50291,
   "<|ht|>": 50339,
@@ -38,7 +38,6 @@
   "<|id|>": 50275,
   "<|is|>": 50311,
   "<|it|>": 50274,
-  "<|iw|>": 50279,
   "<|ja|>": 50266,
   "<|jw|>": 50356,
   "<|ka|>": 50329,

config.json

@@ -2,6 +2,7 @@
   "_name_or_path": "openai/whisper-small",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -11,6 +12,7 @@
     50257
   ],
   "bos_token_id": 50257,
+  "classifier_proj_size": 256,
   "d_model": 768,
   "decoder_attention_heads": 12,
   "decoder_ffn_dim": 3072,
@@ -23,20 +25,128 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
   "max_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,
+  "median_filter_width": 7,
   "model_type": "whisper",
   "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": 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,
+    50360,
+    50361,
+    50362
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "transformers_version": "4.32.0.dev0",
   "use_cache": false,
+  "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99591d01ffe448aca7b7465a534846c741aa43d8046a535428c081c71d96cf7e
-size 967102601
+oid sha256:466f195c5feb6befd08449c9414d8144362e60cc9d660b93c7528174f6f48823
+size 967102729

runs/Jul30_21-45-57_748a1c003589/events.out.tfevents.1690754286.748a1c003589.2285.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f48dd761216626b0d77f0c06cf316e673d65bc2bdddf6107bbc95073860d0fd
+size 9347

special_tokens_map.json

@@ -22,7 +22,7 @@
     "<|hi|>",
     "<|fi|>",
     "<|vi|>",
-    "<|iw|>",
+    "<|he|>",
     "<|uk|>",
     "<|el|>",
     "<|ms|>",
@@ -124,7 +124,7 @@
   },
   "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -9,6 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "eos_token": {
     "__type": "AddedToken",
     "content": "<|endoftext|>",
@@ -19,15 +20,13 @@
   },
   "errors": "replace",
   "model_max_length": 1024,
-  "name_or_path": "openai/whisper-small",
   "pad_token": null,
   "processor_class": "WhisperProcessor",
   "return_attention_mask": false,
-  "special_tokens_map_file": null,
   "tokenizer_class": "WhisperTokenizer",
   "unk_token": {
     "__type": "AddedToken",
-    "content": "",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263926ce703608f7dde9ae8aee16b9d7f67f2e4a55171927bcbcbfd10ecdc647
-size 3579
+oid sha256:ae366487037b6d8e17543ba2ee751902a2bf1d5224020d70db520321aa2ff13e
+size 4155

vocab.json

@@ -314,6 +314,7 @@
   ";;": 35746,
   "<": 27,
   "</": 3433,
+  "<|endoftext|>": 50257,
   "=": 28,
   "=\"": 13114,
   "=\"#": 34106,