joaoalvarenga commited on
Commit
712c30a
0 Parent(s):

first commit

Browse files
.gitattributes ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <<<<<<< HEAD
2
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
3
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
4
+ *.bin filter=lfs diff=lfs merge=lfs -text
5
+ *.h5 filter=lfs diff=lfs merge=lfs -text
6
+ *.tflite filter=lfs diff=lfs merge=lfs -text
7
+ *.tar.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.ot filter=lfs diff=lfs merge=lfs -text
9
+ *.onnx filter=lfs diff=lfs merge=lfs -text
10
+ *.arrow filter=lfs diff=lfs merge=lfs -text
11
+ *.ftz filter=lfs diff=lfs merge=lfs -text
12
+ *.joblib filter=lfs diff=lfs merge=lfs -text
13
+ *.model filter=lfs diff=lfs merge=lfs -text
14
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
15
+ *.pb filter=lfs diff=lfs merge=lfs -text
16
+ *.pt filter=lfs diff=lfs merge=lfs -text
17
+ *.pth filter=lfs diff=lfs merge=lfs -text
18
+ =======
19
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
20
+ >>>>>>> first commit
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 44, "</s>": 45}
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../output/wav2vec2-large-xlsr-portuguese-a/checkpoint-1200",
3
+ "activation_dropout": 0.055,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.094,
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": 0.04,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.047,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.041,
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": 0.082,
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": 43,
74
+ "transformers_version": "4.4.0",
75
+ "vocab_size": 44
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 sha256:569460ce3371a42aaec990cdcf14ebe04e85d508e037b74b2d8b6990bc4b9685
3
+ size 1262103207
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": "../output/wav2vec2-large-xlsr-portuguese-a/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "../output/wav2vec2-large-xlsr-portuguese-a"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"c": 0, "ú": 2, "s": 3, "b": 4, "l": 5, "ã": 6, "â": 7, "ê": 8, "z": 9, "g": 10, "x": 11, "o": 12, "ô": 13, "ü": 14, "w": 15, "h": 16, "ó": 17, "õ": 18, "u": 19, "j": 20, "q": 21, "f": 22, "ç": 23, "í": 24, "r": 25, "ñ": 26, "k": 27, "t": 28, "'": 29, "e": 30, "d": 31, "p": 32, "à": 33, "y": 34, "v": 35, "n": 36, "m": 37, "á": 38, "é": 39, "i": 40, "a": 41, "|": 1, "[UNK]": 42, "[PAD]": 43}