upload ct2 version

added_tokens.json

@@ -0,0 +1,109 @@
+{
+  "<|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,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|iw|>": 50279,
+  "<|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,
+  "<|nocaptions|>": 50362,
+  "<|notimestamps|>": 50363,
+  "<|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,
+  "<|startoflm|>": 50360,
+  "<|startofprev|>": 50361,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50359,
+  "<|translate|>": 50358,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|zh|>": 50260
+}

config.json

@@ -0,0 +1,239 @@
+{
+  "alignment_heads": [
+    [
+      5,
+      3
+    ],
+    [
+      5,
+      9
+    ],
+    [
+      8,
+      0
+    ],
+    [
+      8,
+      4
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      8,
+      8
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      7
+    ],
+    [
+      9,
+      9
+    ],
+    [
+      10,
+      5
+    ]
+  ],
+  "lang_ids": [
+    50259,
+    50260,
+    50261,
+    50262,
+    50263,
+    50264,
+    50265,
+    50266,
+    50267,
+    50268,
+    50269,
+    50270,
+    50271,
+    50272,
+    50273,
+    50274,
+    50275,
+    50276,
+    50277,
+    50278,
+    50279,
+    50280,
+    50281,
+    50282,
+    50283,
+    50284,
+    50285,
+    50286,
+    50287,
+    50288,
+    50289,
+    50290,
+    50291,
+    50292,
+    50293,
+    50294,
+    50295,
+    50296,
+    50297,
+    50298,
+    50299,
+    50300,
+    50301,
+    50302,
+    50303,
+    50304,
+    50305,
+    50306,
+    50307,
+    50308,
+    50309,
+    50310,
+    50311,
+    50312,
+    50313,
+    50314,
+    50315,
+    50316,
+    50317,
+    50318,
+    50319,
+    50320,
+    50321,
+    50322,
+    50323,
+    50324,
+    50325,
+    50326,
+    50327,
+    50328,
+    50329,
+    50330,
+    50331,
+    50332,
+    50333,
+    50334,
+    50335,
+    50336,
+    50337,
+    50338,
+    50339,
+    50340,
+    50341,
+    50342,
+    50343,
+    50344,
+    50345,
+    50346,
+    50347,
+    50348,
+    50349,
+    50350,
+    50351,
+    50352,
+    50353,
+    50354,
+    50355,
+    50356,
+    50357
+  ],
+  "suppress_ids": [
+    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_ids_begin": [
+    220,
+    50257
+  ]
+}

generation_config.json

@@ -0,0 +1,266 @@
+{
+    "alignment_heads": [
+        [
+            5,
+            3
+        ],
+        [
+            5,
+            9
+        ],
+        [
+            8,
+            0
+        ],
+        [
+            8,
+            4
+        ],
+        [
+            8,
+            7
+        ],
+        [
+            8,
+            8
+        ],
+        [
+            9,
+            0
+        ],
+        [
+            9,
+            7
+        ],
+        [
+            9,
+            9
+        ],
+        [
+            10,
+            5
+        ]
+    ],
+    "begin_suppress_tokens": [
+        220,
+        50257
+    ],
+    "bos_token_id": 50257,
+    "decoder_start_token_id": 50258,
+    "eos_token_id": 50257,
+    "forced_decoder_ids": [
+        [
+            1,
+            50265
+        ],
+        [
+            2,
+            50359
+        ]
+    ],
+    "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
+    },
+    "language": "french",
+    "task": "transcribe",
+    "max_initial_timestamp_index": 50,
+    "max_length": 448,
+    "no_timestamps_token_id": 50363,
+    "pad_token_id": 50257,
+    "prev_sot_token_id": 50361,
+    "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,
+        50358,
+        50359,
+        50360,
+        50361,
+        50362
+    ],
+    "task_to_id": {
+        "transcribe": 50359,
+        "translate": 50358
+    },
+    "transformers_version": "4.31.0.dev0"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c714651f943c3a0da71166936e1a337eb983da34e3c1a7f4cb831d91f2548f8
+size 483546977

special_tokens_map.json

@@ -0,0 +1,133 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|iw|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "openai/whisper-small",
+  "pad_token": null,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}