Upload folder using huggingface_hub

bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7846f689d2b2b333dac0ed54353579e7846b95ff52ec066dabb6a20bb8ece8d2
+size 493882

config.json

@@ -0,0 +1,280 @@
+{
+  "transforms": [
+    "huggingface_tokenize"
+  ],
+  "src_vocab_size": 51865,
+  "data": null,
+  "tgt_vocab_size": 51865,
+  "decoder_start_token": "<|startoftranscript|>",
+  "src_vocab": null,
+  "n_sample": 0,
+  "pad_token": "<|endoftext|>",
+  "vocab_size_multiple": 8,
+  "save_data": null,
+  "bos_token": "<|endoftext|>",
+  "tgt_vocab": null,
+  "skip_empty_level": "silent",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>",
+  "share_vocab": true,
+  "training": {
+    "normalization": "tokens",
+    "batch_type": "tokens",
+    "accum_steps": [
+      0
+    ],
+    "valid_batch_size": 256,
+    "quant_type": "",
+    "batch_size_multiple": 1,
+    "group_size": 0,
+    "quant_layers": [],
+    "w_bit": 0,
+    "batch_size": 896,
+    "compute_dtype": "torch.float32",
+    "accum_count": [
+      32
+    ]
+  },
+  "model": {
+    "sliding_window": 4096,
+    "no_timestamps_token_id": 50363,
+    "first_k_dense_replace": 0,
+    "attn_scaling": null,
+    "layer_norm": "standard",
+    "layers": 12,
+    "num_experts": 0,
+    "adapter_bias": false,
+    "num_shared_experts": 0,
+    "add_final_linear_bias": true,
+    "share_decoder_embeddings": true,
+    "left_pad": false,
+    "num_experts_per_tok": 0,
+    "transformer_ff": 3072,
+    "architecture": "whisper",
+    "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
+    ],
+    "parallel_residual": false,
+    "position_encoding_type": "Learned",
+    "add_ffnbias": true,
+    "shared_layer_norm": false,
+    "norm_eps": 1e-05,
+    "heads": 12,
+    "heads_kv": 12,
+    "huggingface_model": "openai/whisper-small",
+    "mlp_activation_fn": "gelu",
+    "hidden_size": 768,
+    "add_key_bias": false,
+    "word_timestamp_heads": [
+      [
+        5,
+        3
+      ],
+      [
+        5,
+        9
+      ],
+      [
+        8,
+        0
+      ],
+      [
+        8,
+        4
+      ],
+      [
+        8,
+        7
+      ],
+      [
+        8,
+        8
+      ],
+      [
+        9,
+        0
+      ],
+      [
+        9,
+        7
+      ],
+      [
+        9,
+        9
+      ],
+      [
+        10,
+        5
+      ]
+    ],
+    "add_qkvbias": true,
+    "moe_transformer_ff": null,
+    "head_dim": null,
+    "begin_suppress_tokens": [
+      220,
+      50257
+    ],
+    "generator_bias": false,
+    "encoder": {
+      "src_word_vec_size": 768,
+      "norm_eps": 1e-05,
+      "sliding_window": 4096,
+      "heads": 12,
+      "heads_kv": 12,
+      "max_source_positions": 1500,
+      "encoder_type": "whisper",
+      "first_k_dense_replace": 0,
+      "mlp_activation_fn": "gelu",
+      "hidden_size": 768,
+      "attn_scaling": null,
+      "add_key_bias": false,
+      "add_qkvbias": true,
+      "layer_norm": "standard",
+      "layers": 12,
+      "num_mel_bins": 80,
+      "moe_transformer_ff": null,
+      "head_dim": null,
+      "num_experts": 0,
+      "num_shared_experts": 0,
+      "add_final_linear_bias": true,
+      "num_experts_per_tok": 0,
+      "transformer_ff": 3072,
+      "position_encoding_type": null,
+      "parallel_residual": false,
+      "add_ffnbias": true,
+      "shared_layer_norm": false
+    },
+    "embeddings": {
+      "src_word_vec_size": 768,
+      "tgt_word_vec_size": 768,
+      "n_positions": 448,
+      "position_encoding_type": "Learned"
+    },
+    "decoder": {
+      "norm_eps": 1e-05,
+      "n_positions": 448,
+      "sliding_window": 4096,
+      "heads": 12,
+      "heads_kv": 12,
+      "first_k_dense_replace": 0,
+      "mlp_activation_fn": "gelu",
+      "tgt_word_vec_size": 768,
+      "hidden_size": 768,
+      "attn_scaling": null,
+      "decoder_type": "transformer",
+      "add_key_bias": false,
+      "add_qkvbias": true,
+      "layers": 12,
+      "layer_norm": "standard",
+      "moe_transformer_ff": null,
+      "head_dim": null,
+      "num_experts": 0,
+      "num_shared_experts": 0,
+      "add_final_linear_bias": true,
+      "num_experts_per_tok": 0,
+      "transformer_ff": 3072,
+      "position_encoding_type": "Learned",
+      "parallel_residual": false,
+      "add_ffnbias": true,
+      "shared_layer_norm": false
+    }
+  },
+  "transforms_configs": {
+    "huggingface_tokenize": {
+      "huggingface_model": "openai/whisper-small",
+      "path": "/scratch/models/whisper-small-eole/tokenizer.json"
+    }
+  },
+  "inference": {
+    "optional_eos": [],
+    "max_length": 448,
+    "chat_template": null
+  }
+}

generation_config.json

@@ -0,0 +1,264 @@
+{
+  "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,
+      null
+    ],
+    [
+      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
+  },
+  "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.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ef4c0c1930adb29d1dc517d7d756258398cc69a0db26edf7e135cb4fd1c023
+size 967000200

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7734884874f1a1513ed9aa760a4f8e97aaa02fd6d93a3a85d27b2ae9ca596b
+size 966995080

special_tokens_map.json

@@ -0,0 +1,139 @@
+{
+  "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|>",
+    "<|he|>",
+    "<|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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}