From 0956b0746307aca2dded1f4f1393c4e6c927c3ae Mon Sep 17 00:00:00 2001 From: maxidl Date: Sun, 28 Mar 2021 21:43:59 +0200 Subject: [PATCH] Add model files --- config.json | 76 ++++++++++++++++++++++++++++++++++++++++ preprocessor_config.json | 8 +++++ pytorch_model.bin | 3 ++ special_tokens_map.json | 1 + tokenizer_config.json | 1 + vocab.json | 1 + 6 files changed, 90 insertions(+) create mode 100644 config.json create mode 100644 preprocessor_config.json create mode 100644 pytorch_model.bin create mode 100644 special_tokens_map.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/config.json b/config.json new file mode 100644 index 0000000..7faf06f --- /dev/null +++ b/config.json @@ -0,0 +1,76 @@ +{ + "_name_or_path": "facebook/wav2vec2-large-xlsr-53", + "activation_dropout": 0.055, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2ForCTC" + ], + "attention_dropout": 0.094, + "bos_token_id": 1, + "conv_bias": true, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "mean", + "ctc_zero_infinity": false, + "do_stable_layer_norm": true, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "layer", + "feat_proj_dropout": 0.04, + "final_dropout": 0.0, + "gradient_checkpointing": true, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "layerdrop": 0.04, + "mask_channel_length": 10, + "mask_channel_min_space": 1, + "mask_channel_other": 0.0, + "mask_channel_prob": 0.0, + "mask_channel_selection": "static", + "mask_feature_length": 10, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_space": 1, + "mask_time_other": 0.0, + "mask_time_prob": 0.08, + "mask_time_selection": "static", + "model_type": "wav2vec2", + "num_attention_heads": 16, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 24, + "pad_token_id": 171, + "transformers_version": "4.4.2", + "vocab_size": 174 +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..0886a48 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,8 @@ +{ + "do_normalize": true, + "feature_size": 1, + "padding_side": "right", + "padding_value": 0.0, + "return_attention_mask": true, + "sampling_rate": 16000 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..591bcfb --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07eae28d0b3f8b8b9467271d3b73250b47009f683dfe7f7bc18bfca37b5668d5 +size 1262647255 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9abf719 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "unk_token": "[UNK]", "pad_token": "[PAD]"} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a2a8340 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"unk_token": "[UNK]", "bos_token": "", "eos_token": "", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"} \ No newline at end of file diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..e8c7c96 --- /dev/null +++ b/vocab.json @@ -0,0 +1 @@ +{"к": 0, "„": 1, "⟩": 2, "ą": 3, "‟": 4, "о": 5, "臣": 6, "å": 7, "_": 8, "ğ": 9, "ï": 10, "x": 11, "ź": 12, "ç": 13, "ö": 14, "´": 15, "ë": 16, "ä": 17, "t": 18, "f": 19, "ň": 20, "ť": 21, "ņ": 22, "ü": 23, "s": 24, "е": 25, "ả": 26, "b": 27, "в": 28, "ū": 29, "q": 30, "ț": 31, "̆": 32, "≡": 33, "̇": 34, "ś": 35, "孙": 36, "ṟ": 38, "i": 39, "û": 40, "ō": 41, "`": 42, "z": 43, "‑": 44, "ན": 45, "ù": 46, "r": 47, "и": 48, "″": 49, "ọ": 50, "e": 51, "w": 52, "ạ": 53, "a": 54, "比": 55, "ʻ": 56, "°": 57, "d": 58, "ī": 59, "g": 60, "k": 61, "カ": 62, "ч": 63, "=": 64, "ż": 65, "ħ": 66, "o": 67, "ñ": 68, "ô": 69, "ď": 70, "ø": 71, "ž": 72, "y": 73, "ý": 74, "ș": 75, "ḫ": 76, "ó": 77, "ē": 78, "ő": 79, "無": 80, "à": 81, "ş": 82, "→": 83, "ộ": 84, "с": 85, "ắ": 86, "ê": 87, "”": 88, "ă": 89, "幺": 90, "é": 91, "h": 92, "′": 93, "ř": 94, "]": 95, "尣": 96, "乡": 97, "á": 98, "æ": 99, "ǐ": 100, "ı": 101, "[": 102, "î": 103, "u": 104, "’": 105, "č": 106, "⟨": 107, "p": 108, "ę": 109, "l": 110, "ā": 111, "ằ": 112, "c": 113, "š": 114, "“": 115, "临": 116, "ѹ": 117, "ć": 118, "ṭ": 119, "ŏ": 120, "m": 121, "ě": 122, "¡": 123, "ů": 124, "‹": 125, "…": 126, "道": 127, "་": 128, "м": 129, "v": 130, "ń": 131, "р": 132, "ф": 133, "‘": 134, "›": 135, "»": 136, "ð": 137, "«": 138, "支": 139, "þ": 140, "ế": 141, "ễ": 142, "ʿ": 143, "ġ": 144, "í": 145, "ß": 146, "–": 147, "ú": 148, "ứ": 149, "ə": 150, "n": 151, "а": 152, "ш": 153, "đ": 154, "‚": 155, "ã": 156, "â": 157, "œ": 158, "−": 159, "µ": 160, "—": 161, "ṣ": 162, "õ": 163, "ò": 164, "辶": 165, "j": 166, "ì": 167, "ė": 168, "ł": 169, "|": 37, "[UNK]": 170, "[PAD]": 171} \ No newline at end of file