Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./whisper-small",
+  "_name_or_path": "./whisper-large-v3",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -13,32 +13,18 @@
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 32,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 32,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -52,101 +38,13 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 12,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
   "scale_embedding": false,
-  "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": "4.42.3",
   "use_cache": true,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 51866
 }

preprocessor_config.json

@@ -1,7 +1,7 @@
 {
   "chunk_length": 30,
   "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 80,
+  "feature_size": 128,
   "hop_length": 160,
   "n_fft": 400,
   "n_samples": 480000,

runs/Aug07_13-22-47_gaussian/events.out.tfevents.1723008169.gaussian.9555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a0edd1e91b9b9d4ef41c089fcf9a01a83d9e4ad12b048089c70990208313d7
+size 10258

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02f9a4204071e497b5e3220eba2deb739575461769acb62babea3e0212c6835
+oid sha256:5a6bab565198b51533844f1ab2b355ee89355bf1722de7c488411d2fbda1f388
 size 5368