joaoalvarenga commited on
Commit
ce4dd61
1 Parent(s): 02c5d42

first version

Browse files
.gitattributes CHANGED
@@ -14,3 +14,4 @@
14
  *.pb filter=lfs diff=lfs merge=lfs -text
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
 
 
14
  *.pb filter=lfs diff=lfs merge=lfs -text
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
17
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 147, "</s>": 148}
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/joaoalvarenga/wav2vec2-large-xlsr-italian/checkpoint-9800",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "conv_bias": true,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "mean",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": true,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_dropout": 0.0,
44
+ "feat_extract_norm": "layer",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_channel_length": 10,
56
+ "mask_channel_min_space": 1,
57
+ "mask_channel_other": 0.0,
58
+ "mask_channel_prob": 0.0,
59
+ "mask_channel_selection": "static",
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_space": 1,
64
+ "mask_time_other": 0.0,
65
+ "mask_time_prob": 0.05,
66
+ "mask_time_selection": "static",
67
+ "model_type": "wav2vec2",
68
+ "num_attention_heads": 16,
69
+ "num_conv_pos_embedding_groups": 16,
70
+ "num_conv_pos_embeddings": 128,
71
+ "num_feat_extract_layers": 7,
72
+ "num_hidden_layers": 24,
73
+ "pad_token_id": 146,
74
+ "transformers_version": "4.4.0",
75
+ "vocab_size": 147
76
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": true,
7
+ "sampling_rate": 16000
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1325e6e6dca4a5fa6e6a615c0fc13bf0015eb0675476a0c8be7b79163ab359
3
+ size 1262525543
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/home/joaoalvarenga/wav2vec2-large-xlsr-italian/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/joaoalvarenga/wav2vec2-large-xlsr-italian"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"w": 0, "ş": 1, "ʿ": 2, "л": 3, "ъ": 4, "»": 5, "̇": 6, "đ": 7, "ì": 8, "ã": 9, "æ": 10, "°": 11, "ț": 12, "s": 13, "t": 14, ">": 15, "«": 16, "[": 17, "е": 18, "ン": 19, "r": 20, "o": 21, "l": 23, "´": 24, "ś": 25, "ʻ": 26, "¡": 27, "カ": 28, "ñ": 29, "ו": 30, "<": 31, "ī": 32, "…": 33, "ô": 34, "ø": 35, "ṭ": 36, "f": 37, "ð": 38, "多": 39, "б": 40, "ё": 41, "ř": 42, "ő": 43, "丰": 44, "ı": 45, "í": 46, "c": 47, "万": 48, "š": 49, "ė": 50, "ō": 51, "=": 52, "é": 53, ")": 54, "y": 55, "þ": 56, "ṣ": 57, "/": 58, "(": 59, "–": 60, "張": 61, "å": 62, "ě": 63, "а": 64, "ה": 65, "ü": 66, "e": 67, "ö": 68, "á": 69, "~": 70, "`": 71, "ū": 72, "i": 73, "g": 74, "ß": 75, "_": 76, "’": 77, "峰": 78, "u": 79, "あ": 80, "ň": 81, "ノ": 82, "q": 83, "+": 84, "ú": 85, "ÿ": 86, "ê": 87, "p": 88, "ž": 89, "$": 90, "z": 91, "ʼ": 92, "ц": 93, "č": 94, "ア": 95, "ṛ": 96, "x": 97, "三": 98, "љ": 99, "ù": 100, "ò": 101, "ź": 102, "ľ": 103, "ń": 104, "û": 105, "#": 106, "j": 107, "„": 108, "î": 109, "ḥ": 110, "ー": 111, "h": 112, "è": 113, "禅": 114, "'": 115, "à": 116, "ë": 117, "m": 118, "ł": 119, "ד": 120, "d": 121, "ʾ": 122, "ę": 123, "ā": 124, "ğ": 125, "ï": 126, "]": 127, "旅": 128, "ə": 129, "b": 130, "ć": 131, "ʹ": 132, "サ": 133, "µ": 134, "ä": 135, "œ": 136, "v": 137, "キ": 138, "古": 139, "ș": 140, "n": 141, "k": 142, "ó": 143, "a": 144, "|": 22, "[UNK]": 145, "[PAD]": 146}