Upload 11 files

config.json

@@ -1,48 +1,50 @@
-{
-  "_name_or_path": "openai/whisper-large-v3",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "apply_spec_augment": true,
-  "architectures": [
-    "WhisperForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "begin_suppress_tokens": null,
-  "bos_token_id": 50257,
-  "classifier_proj_size": 256,
-  "d_model": 1280,
-  "decoder_attention_heads": 20,
-  "decoder_ffn_dim": 5120,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 20,
-  "encoder_ffn_dim": 5120,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 32,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": null,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
-  "max_length": null,
-  "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,
-  "scale_embedding": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.0.dev0",
-  "use_cache": true,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 51866
-}
+{
+  "_name_or_path": "/Users/SEPINF/Desktop/whsiper-large-v3-finetuned/",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "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,
+  "scale_embedding": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

generation_config.json

@@ -1,257 +1,265 @@
-{
-  "alignment_heads": [
-    [
-      7,
-      0
-    ],
-    [
-      10,
-      17
-    ],
-    [
-      12,
-      18
-    ],
-    [
-      13,
-      12
-    ],
-    [
-      16,
-      1
-    ],
-    [
-      17,
-      14
-    ],
-    [
-      19,
-      11
-    ],
-    [
-      21,
-      4
-    ],
-    [
-      24,
-      1
-    ],
-    [
-      25,
-      6
-    ]
-  ],
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
-  "bos_token_id": 50257,
-  "decoder_start_token_id": 50258,
-  "eos_token_id": 50257,
-  "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,
-    "<|yue|>": 50358,
-    "<|zh|>": 50260
-  },
-  "language": "portuguese",
-  "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
-  ],
-  "task": "transcribe",
-  "task_to_id": {
-    "transcribe": 50360,
-    "translate": 50359
-  },
-  "transformers_version": "4.45.0.dev0"
-}
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "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,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "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
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.44.0"
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242ddaa463a64ced245bd1a75f41ebe2270e2d2ac6d434f748e8c72719472b7c
+oid sha256:c8ad6a0e63752a22faeb79f4d9b167a129d4e60f417a4463e08279d3ec302355
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c21aaa3c64158023633b474a22a98400eb1876dea9acdee8740d5d24136ba5a
+oid sha256:637b9cd6bcf4579bfda547ca67a09f3a7f489cedfbf23c8581e9f20e7a33e9a8
 size 1180663192

preprocessor_config.json

@@ -1,14 +1,14 @@
-{
-  "chunk_length": 30,
-  "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 128,
-  "hop_length": 160,
-  "n_fft": 400,
-  "n_samples": 480000,
-  "nb_max_frames": 3000,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "processor_class": "WhisperProcessor",
-  "return_attention_mask": false,
-  "sampling_rate": 16000
-}
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -1,139 +1,139 @@
-{
-  "additional_special_tokens": [
-    "<|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|>",
-    "<|yue|>",
-    "<|translate|>",
-    "<|transcribe|>",
-    "<|startoflm|>",
-    "<|startofprev|>",
-    "<|nospeech|>",
-    "<|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
-  }
-}
+{
+  "additional_special_tokens": [
+    "<|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|>",
+    "<|yue|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nospeech|>",
+    "<|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
+  }
+}