Training in progress, step 1000

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,
@@ -23,9 +25,28 @@
   "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,
@@ -34,9 +55,97 @@
   "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": "4.27.0.dev0",
+  "transformers_version": "4.28.0.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 sha256:8474fb4672037e2f27b948f9bfd8eb53f5cadc4fcdb558259babf301c3f70562
+oid sha256:77de2f273fbb64ffb52fee19479e7e444a0f409c04339a53f138389bf3427cec
 size 967102601

runs/Apr12_13-11-29_f2fac5cc40a1/1681305629.9984689/events.out.tfevents.1681305629.f2fac5cc40a1.879.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38aa0baae3d79614fa74c75e64f4054bad110a5d0d39499fc69941e3de9418c
+size 6190

runs/Apr12_13-11-29_f2fac5cc40a1/events.out.tfevents.1681305629.f2fac5cc40a1.879.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543628b4e30cbb04cec94f368ee8298e150e9779f911e77df1fee70a2d4e0ebc
+size 12350

tokenizer_config.json

@@ -9,6 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "eos_token": {
     "__type": "AddedToken",
     "content": "<|endoftext|>",
@@ -22,7 +23,6 @@
   "pad_token": null,
   "processor_class": "WhisperProcessor",
   "return_attention_mask": false,
-  "special_tokens_map_file": null,
   "tokenizer_class": "WhisperTokenizer",
   "unk_token": {
     "__type": "AddedToken",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456baabb179908b7f0efb7092ef1117bfe7a433f254e0d46130d9248691992b0
-size 3643
+oid sha256:36ad6055df4a2a87fddc0ec298450339465cd364cf3bbfecec0f77ac97847156
+size 3771