Delete files * with huggingface_hub

README.md

@@ -1,3 +0,0 @@
----
-license: mit
----

config.json

@@ -1,153 +0,0 @@
-{
-  "_name_or_path": "openai/whisper-tiny",
-  "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": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
-  "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": 4,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": 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
-  ],
-  "transformers_version": "4.38.2",
-  "use_cache": true,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 51865
-}

decoder_with_past_model.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c51c9c39e16dfc87dc2943a814df827731d8d1c4ca0ba952dcfe7fdecf0dfaa
-size 56961977

encoder_model.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc4bf9f3fadc450b128c3ef0711a4e61a55797447b6a700abe7fb97d9f549518
-size 16519192

generation_config.json

@@ -1,249 +0,0 @@
-{
-  "alignment_heads": [
-    [
-      2,
-      2
-    ],
-    [
-      3,
-      0
-    ],
-    [
-      3,
-      2
-    ],
-    [
-      3,
-      3
-    ],
-    [
-      3,
-      4
-    ],
-    [
-      3,
-      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": "4.38.2",
-  "trust_remote_code": false
-}

model_metadata.json

@@ -1,74 +0,0 @@
-{
-  "model_id": "whisper-tiny",
-  "version": "1.0",
-  "description": "Whisper-tiny multilingual ASR model (onnx-community/whisper-tiny)",
-  "execution_template": {
-    "type": "Pipeline",
-    "stages": [
-      {
-        "name": "encoder",
-        "model_file": "encoder_model.onnx",
-        "execution_mode": {
-          "type": "SingleShot"
-        },
-        "inputs": ["input_features"],
-        "outputs": ["last_hidden_state"]
-      },
-      {
-        "name": "decoder",
-        "model_file": "decoder_with_past_model.onnx",
-        "execution_mode": {
-          "type": "WhisperDecoder",
-          "max_tokens": 448,
-          "start_token_id": 50258,
-          "end_token_id": 50257,
-          "language_token_id": 50259,
-          "task_token_id": 50359,
-          "no_timestamps_token_id": 50363,
-          "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],
-          "repetition_penalty": 1.1
-        },
-        "inputs": ["input_ids", "encoder_hidden_states"],
-        "outputs": ["logits"]
-      }
-    ],
-    "config": {
-      "num_layers": 4,
-      "num_heads": 6,
-      "head_dim": 64,
-      "hidden_size": 384,
-      "encoder_seq_len": 1500,
-      "vocab_size": 51865
-    }
-  },
-  "preprocessing": [
-    {
-      "type": "MelSpectrogram",
-      "n_mels": 80,
-      "sample_rate": 16000,
-      "fft_size": 400,
-      "hop_length": 160
-    }
-  ],
-  "postprocessing": [
-    {
-      "type": "WhisperDecode",
-      "tokenizer_file": "tokenizer.json"
-    }
-  ],
-  "files": [
-    "encoder_model.onnx",
-    "decoder_with_past_model.onnx",
-    "tokenizer.json",
-    "config.json",
-    "generation_config.json"
-  ],
-  "metadata": {
-    "task": "automatic-speech-recognition",
-    "language": "multilingual",
-    "sample_rate": 16000,
-    "max_audio_length_seconds": 30,
-    "license": "MIT",
-    "source": "onnx-community/whisper-tiny"
-  }
-}

preprocessor_config.json

@@ -1,14 +0,0 @@
-{
-  "chunk_length": 30,
-  "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 80,
-  "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
-}