Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-medium",
+  "_name_or_path": "distil-whisper/distil-large-v3",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -13,32 +13,19 @@
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 24,
+  "decoder_layers": 2,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 24,
+  "encoder_layers": 32,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
+  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -52,103 +39,14 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 24,
-  "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,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
+  "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
-  "use_cache": false,
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 51866
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ecf09cf73ed66bb6342fa32bbad38581c441edd6ed78218666551f10c274aa
-size 3055544304
+oid sha256:2bb6b0ab1faa3ef6ec1e83a62a5a94faa7e53ba1c14357bc73f9f90e805f8975
+size 3025686376

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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0133dc206bc8ddf1070d381929df4dc85cc255450e8746826161000475900106
-size 5112
+oid sha256:dc60a7e80170a0293612358072f9855b2cf83d470047df79d762ef4d5ad18f87
+size 5240