patrickvonplaten commited on
Commit
d5ee9b1
1 Parent(s): 0bc97c0

upload correct weights

Browse files
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForCTC"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "conv_bias": true,
10
+ "conv_dim": [
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512
18
+ ],
19
+ "conv_kernel": [
20
+ 10,
21
+ 3,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 2,
26
+ 2
27
+ ],
28
+ "conv_stride": [
29
+ 5,
30
+ 2,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2
36
+ ],
37
+ "ctc_loss_reduction": "sum",
38
+ "ctc_zero_infinity": false,
39
+ "do_stable_layer_norm": true,
40
+ "eos_token_id": 2,
41
+ "feat_extract_activation": "gelu",
42
+ "feat_extract_dropout": 0.0,
43
+ "feat_extract_norm": "layer",
44
+ "feat_proj_dropout": 0.1,
45
+ "final_dropout": 0.0,
46
+ "gradient_checkpointing": false,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_size": 1024,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 4096,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.1,
54
+ "mask_channel_length": 10,
55
+ "mask_channel_min_space": 1,
56
+ "mask_channel_other": 0.0,
57
+ "mask_channel_prob": 0.0,
58
+ "mask_channel_selection": "static",
59
+ "mask_feature_length": 10,
60
+ "mask_feature_prob": 0.0,
61
+ "mask_time_length": 10,
62
+ "mask_time_min_space": 1,
63
+ "mask_time_other": 0.0,
64
+ "mask_time_prob": 0.075,
65
+ "mask_time_selection": "static",
66
+ "model_type": "wav2vec2",
67
+ "num_attention_heads": 16,
68
+ "num_conv_pos_embedding_groups": 16,
69
+ "num_conv_pos_embeddings": 128,
70
+ "num_feat_extract_layers": 7,
71
+ "num_hidden_layers": 24,
72
+ "pad_token_id": 0,
73
+ "transformers_version": "4.5.0.dev0",
74
+ "vocab_size": 42
75
+ }
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 sha256:4da85885e94ef52eb8ae0419c0711b922e81e55e4a4f07f2b445236243ca9902
3
+ size 1262100119
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/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-polish/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-polish"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "A": 5, "I": 6, "E": 7, "O": 8, "Z": 9, "N": 10, "S": 11, "W": 12, "R": 13, "C": 14, "Y": 15, "M": 16, "T": 17, "D": 18, "K": 19, "P": 20, "Ł": 21, "J": 22, "U": 23, "L": 24, "B": 25, "Ę": 26, "G": 27, "Ą": 28, "Ż": 29, "H": 30, "Ś": 31, "Ó": 32, "Ć": 33, "F": 34, "Ń": 35, "Ź": 36, "V": 37, "-": 38, "Q": 39, "X": 40, "'": 41}