Upload WhisperForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "openai/whisper-small.en",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -9,7 +9,7 @@
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
     220,
-    50257
+    50256
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -18,13 +18,13 @@
   "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "decoder_start_token_id": 50258,
+  "decoder_start_token_id": 50257,
   "dropout": 0.0,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
-  "eos_token_id": 50257,
+  "eos_token_id": 50256,
   "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
@@ -41,12 +41,12 @@
   "model_type": "whisper",
   "num_hidden_layers": 12,
   "num_mel_bins": 80,
-  "pad_token_id": 50257,
+  "pad_token_id": 50256,
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.36.0.dev0",
+  "transformers_version": "4.37.0.dev0",
   "use_cache": false,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 51864
 }

generation_config.json

@@ -1,170 +1,100 @@
 {
   "alignment_heads": [
     [
-      5,
+      6,
+      6
+    ],
+    [
+      7,
+      0
+    ],
+    [
+      7,
       3
     ],
     [
-      5,
-      9
+      7,
+      8
     ],
     [
       8,
-      0
+      2
     ],
     [
       8,
-      4
+      5
     ],
     [
       8,
       7
     ],
     [
-      8,
-      8
+      9,
+      0
     ],
     [
       9,
-      0
+      4
     ],
     [
       9,
-      7
+      8
     ],
     [
       9,
-      9
+      10
     ],
     [
       10,
-      5
+      0
+    ],
+    [
+      10,
+      1
+    ],
+    [
+      10,
+      2
+    ],
+    [
+      10,
+      3
+    ],
+    [
+      10,
+      6
+    ],
+    [
+      10,
+      11
+    ],
+    [
+      11,
+      2
+    ],
+    [
+      11,
+      4
     ]
   ],
   "begin_suppress_tokens": [
     220,
-    50257
+    50256
   ],
   "bos_token_id": 50257,
-  "decoder_start_token_id": 50258,
-  "eos_token_id": 50257,
+  "decoder_start_token_id": 50257,
+  "eos_token_id": 50256,
   "forced_decoder_ids": [
     [
       1,
-      null
-    ],
-    [
-      2,
-      50359
+      50362
     ]
   ],
-  "is_multilingual": true,
-  "lang_to_id": {
-    "<|af|>": 50327,
-    "<|am|>": 50334,
-    "<|ar|>": 50272,
-    "<|as|>": 50350,
-    "<|az|>": 50304,
-    "<|ba|>": 50355,
-    "<|be|>": 50330,
-    "<|bg|>": 50292,
-    "<|bn|>": 50302,
-    "<|bo|>": 50347,
-    "<|br|>": 50309,
-    "<|bs|>": 50315,
-    "<|ca|>": 50270,
-    "<|cs|>": 50283,
-    "<|cy|>": 50297,
-    "<|da|>": 50285,
-    "<|de|>": 50261,
-    "<|el|>": 50281,
-    "<|en|>": 50259,
-    "<|es|>": 50262,
-    "<|et|>": 50307,
-    "<|eu|>": 50310,
-    "<|fa|>": 50300,
-    "<|fi|>": 50277,
-    "<|fo|>": 50338,
-    "<|fr|>": 50265,
-    "<|gl|>": 50319,
-    "<|gu|>": 50333,
-    "<|haw|>": 50352,
-    "<|ha|>": 50354,
-    "<|he|>": 50279,
-    "<|hi|>": 50276,
-    "<|hr|>": 50291,
-    "<|ht|>": 50339,
-    "<|hu|>": 50286,
-    "<|hy|>": 50312,
-    "<|id|>": 50275,
-    "<|is|>": 50311,
-    "<|it|>": 50274,
-    "<|ja|>": 50266,
-    "<|jw|>": 50356,
-    "<|ka|>": 50329,
-    "<|kk|>": 50316,
-    "<|km|>": 50323,
-    "<|kn|>": 50306,
-    "<|ko|>": 50264,
-    "<|la|>": 50294,
-    "<|lb|>": 50345,
-    "<|ln|>": 50353,
-    "<|lo|>": 50336,
-    "<|lt|>": 50293,
-    "<|lv|>": 50301,
-    "<|mg|>": 50349,
-    "<|mi|>": 50295,
-    "<|mk|>": 50308,
-    "<|ml|>": 50296,
-    "<|mn|>": 50314,
-    "<|mr|>": 50320,
-    "<|ms|>": 50282,
-    "<|mt|>": 50343,
-    "<|my|>": 50346,
-    "<|ne|>": 50313,
-    "<|nl|>": 50271,
-    "<|nn|>": 50342,
-    "<|no|>": 50288,
-    "<|oc|>": 50328,
-    "<|pa|>": 50321,
-    "<|pl|>": 50269,
-    "<|ps|>": 50340,
-    "<|pt|>": 50267,
-    "<|ro|>": 50284,
-    "<|ru|>": 50263,
-    "<|sa|>": 50344,
-    "<|sd|>": 50332,
-    "<|si|>": 50322,
-    "<|sk|>": 50298,
-    "<|sl|>": 50305,
-    "<|sn|>": 50324,
-    "<|so|>": 50326,
-    "<|sq|>": 50317,
-    "<|sr|>": 50303,
-    "<|su|>": 50357,
-    "<|sv|>": 50273,
-    "<|sw|>": 50318,
-    "<|ta|>": 50287,
-    "<|te|>": 50299,
-    "<|tg|>": 50331,
-    "<|th|>": 50289,
-    "<|tk|>": 50341,
-    "<|tl|>": 50348,
-    "<|tr|>": 50268,
-    "<|tt|>": 50351,
-    "<|uk|>": 50280,
-    "<|ur|>": 50290,
-    "<|uz|>": 50337,
-    "<|vi|>": 50278,
-    "<|yi|>": 50335,
-    "<|yo|>": 50325,
-    "<|zh|>": 50260
-  },
+  "is_multilingual": false,
   "max_initial_timestamp_index": 1,
   "max_length": 448,
-  "no_timestamps_token_id": 50363,
-  "pad_token_id": 50257,
-  "return_timestamps": false,
+  "no_timestamps_token_id": 50362,
+  "pad_token_id": 50256,
   "suppress_tokens": [
     1,
     2,
@@ -189,75 +119,73 @@
     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,
+    357,
+    366,
+    438,
+    532,
+    685,
+    705,
+    796,
+    930,
+    1058,
+    1220,
+    1267,
+    1279,
+    1303,
+    1343,
+    1377,
+    1391,
+    1635,
+    1782,
+    1875,
+    2162,
+    2361,
+    2488,
+    3467,
+    4008,
+    4211,
+    4600,
+    4808,
+    5299,
+    5855,
+    6329,
+    7203,
+    9609,
+    9959,
+    10563,
+    10786,
+    11420,
+    11709,
+    11907,
+    13163,
+    13697,
+    13700,
+    14808,
+    15306,
+    16410,
+    16791,
+    17992,
+    19203,
+    19510,
+    20724,
+    22305,
+    22935,
+    27007,
+    30109,
+    30420,
+    33409,
+    34949,
+    40283,
+    40493,
+    40549,
+    47282,
+    49146,
+    50257,
+    50357,
     50358,
     50359,
     50360,
-    50361,
-    50362
+    50361
   ],
-  "task_to_id": {
-    "transcribe": 50359,
-    "translate": 50358
-  },
-  "transformers_version": "4.36.0.dev0"
+  "transformers_version": "4.37.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd92efd19ccde96900f6a5147ec797486a91337b15c7521f30915cc74e744b6
-size 966995080
+oid sha256:e26002565dd3d190bb4d986e83501a9761279a2307b9828dc0d020e7e44d0db7
+size 966992008