Training in progress, step 100

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,
@@ -26,6 +28,12 @@
   "forced_decoder_ids": null,
   "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,
@@ -36,7 +44,8 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "transformers_version": "4.29.0.dev0",
   "use_cache": true,
+  "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06df0657d9864188bc436e4406c3fbe06fb186c10738a83c59be4d201f73e051
+oid sha256:29294075f1bdbc0287381bc41225d0dd039ccf302b349ca1d917da64ed09833e
 size 967102601

runs/May04_20-59-03_l1055-28/1683214277.409688/events.out.tfevents.1683214277.l1055-28.85383.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfcc4a6fdf5f3ecc2038b80d4583a3e083143459496f93e8b66e7f0539678618
+size 6172

runs/May04_20-59-03_l1055-28/events.out.tfevents.1683214277.l1055-28.85383.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bf416482ec9bfe0927201452c7f761196fdc300b6049056f652a131302f8d6
+size 5717

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 sha256:7b7bfb6abde1a1f673ce7185d9c88f66c03bdad1243a28041bb0686091222128
-size 3643
+oid sha256:c93b3d09cc403c1ea7750abb24ee4622ea9fc275e60e04453b3f4dfdfb55a874
+size 4091

vocab.json

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