lgris commited on
Commit
718456c
1 Parent(s): 5ef732c

first commit

Browse files
.gitattributes CHANGED
@@ -15,3 +15,4 @@
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
17
  *tfevents* 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
  *tfevents* filter=lfs diff=lfs merge=lfs -text
18
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53-portuguese",
3
+ "activation_dropout": 0.1,
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": "sum",
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": 0.1,
46
+ "final_dropout": 0.1,
47
+ "gradient_checkpointing": false,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
50
+ "hidden_dropout_prob": 0.1,
51
+ "hidden_size": 1024,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "layerdrop": 0.1,
56
+ "mask_feature_length": 10,
57
+ "mask_feature_prob": 0.0,
58
+ "mask_time_length": 10,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "wav2vec2",
61
+ "num_attention_heads": 16,
62
+ "num_conv_pos_embedding_groups": 16,
63
+ "num_conv_pos_embeddings": 128,
64
+ "num_feat_extract_layers": 7,
65
+ "num_hidden_layers": 24,
66
+ "pad_token_id": 0,
67
+ "transformers_version": "4.6.1",
68
+ "vocab_size": 44
69
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e0a5a233bf51a5d7e71c61dde967d3a0dd78a4348bb99acb328a08bc1e55b6
3
+ size 1262108311
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": "|"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "A": 5, "E": 6, "O": 7, "S": 8, "R": 9, "I": 10, "N": 11, "D": 12, "M": 13, "T": 14, "U": 15, "C": 16, "L": 17, "P": 18, "V": 19, "G": 20, "F": 21, "H": 22, "Q": 23, "B": 24, "Ã": 25, "Ç": 26, "É": 27, "Á": 28, "Z": 29, "J": 30, "X": 31, "Í": 32, "Ó": 33, "Ê": 34, "-": 35, "Õ": 36, "À": 37, "Ú": 38, "Ô": 39, "Â": 40, "Y": 41, "K": 42, "W": 43}
wav2vec_brazilian_portuguese.ipynb ADDED
The diff for this file is too large to render. See raw diff