Upload WhisperForConditionalGeneration

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openai/whisper-large-v3",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -9,7 +8,7 @@
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
     220,
-    50257
+    50256
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -17,7 +16,7 @@
   "decoder_attention_heads": 20,
   "decoder_ffn_dim": 5120,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
+  "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
   "encoder_attention_heads": 20,
@@ -34,18 +33,16 @@
   "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": 32,
   "num_mel_bins": 128,
-  "pad_token_id": 50256,
+  "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.36.0.dev0",
+  "transformers_version": "4.56.0.dev0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51866

generation_config.json

@@ -1,44 +1,28 @@
 {
   "alignment_heads": [
     [
-      7,
-      0
-    ],
-    [
-      10,
-      17
-    ],
-    [
-      12,
-      18
+      2,
+      4
     ],
     [
-      13,
-      12
+      2,
+      11
     ],
     [
-      16,
-      1
+      3,
+      3
     ],
     [
-      17,
-      14
+      3,
+      6
     ],
     [
-      19,
+      3,
       11
     ],
     [
-      21,
-      4
-    ],
-    [
-      24,
-      1
-    ],
-    [
-      25,
-      6
+      3,
+      14
     ]
   ],
   "begin_suppress_tokens": [
@@ -161,104 +145,16 @@
     "<|yue|>": 50358,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50364,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
   "return_timestamps": 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,
-    50359,
-    50360,
-    50361,
-    50362,
-    50363
-  ],
+  "suppress_tokens": [],
   "task_to_id": {
     "transcribe": 50360,
     "translate": 50359
   },
-  "transformers_version": "4.36.0.dev0"
+  "transformers_version": "4.56.0.dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2ece75ee449a288d23b728b1bd32d4a150c3c71550301d2e780af1cde69c9a
+size 3235581408