Commit
•
a0bdc50
1
Parent(s):
17b5005
Upload tiny models for UniSpeechSatModel
Browse files- config.json +82 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +16 -0
- vocab.json +34 -0
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"apply_spec_augment": true,
|
4 |
+
"architectures": [
|
5 |
+
"UniSpeechSatModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"classifier_proj_size": 256,
|
10 |
+
"codevector_dim": 256,
|
11 |
+
"contrastive_logits_temperature": 0.1,
|
12 |
+
"conv_bias": false,
|
13 |
+
"conv_dim": [
|
14 |
+
32,
|
15 |
+
32,
|
16 |
+
32
|
17 |
+
],
|
18 |
+
"conv_kernel": [
|
19 |
+
8,
|
20 |
+
8,
|
21 |
+
8
|
22 |
+
],
|
23 |
+
"conv_stride": [
|
24 |
+
4,
|
25 |
+
4,
|
26 |
+
4
|
27 |
+
],
|
28 |
+
"ctc_loss_reduction": "mean",
|
29 |
+
"ctc_zero_infinity": false,
|
30 |
+
"diversity_loss_weight": 0.1,
|
31 |
+
"do_stable_layer_norm": false,
|
32 |
+
"eos_token_id": 2,
|
33 |
+
"feat_extract_activation": "gelu",
|
34 |
+
"feat_extract_dropout": 0.0,
|
35 |
+
"feat_extract_norm": "group",
|
36 |
+
"feat_proj_dropout": 0.0,
|
37 |
+
"feat_quantizer_dropout": 0.0,
|
38 |
+
"final_dropout": 0.1,
|
39 |
+
"hidden_act": "gelu",
|
40 |
+
"hidden_dropout": 0.1,
|
41 |
+
"hidden_dropout_prob": 0.1,
|
42 |
+
"hidden_size": 16,
|
43 |
+
"initializer_range": 0.02,
|
44 |
+
"intermediate_size": 20,
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
+
"layerdrop": 0.1,
|
47 |
+
"mask_feature_length": 10,
|
48 |
+
"mask_feature_min_masks": 0,
|
49 |
+
"mask_feature_prob": 0.0,
|
50 |
+
"mask_time_length": 2,
|
51 |
+
"mask_time_min_masks": 2,
|
52 |
+
"mask_time_prob": 0.5,
|
53 |
+
"model_type": "unispeech-sat",
|
54 |
+
"num_attention_heads": 2,
|
55 |
+
"num_clusters": 504,
|
56 |
+
"num_codevector_groups": 2,
|
57 |
+
"num_codevectors_per_group": 320,
|
58 |
+
"num_conv_pos_embedding_groups": 2,
|
59 |
+
"num_conv_pos_embeddings": 16,
|
60 |
+
"num_feat_extract_layers": 3,
|
61 |
+
"num_hidden_layers": 4,
|
62 |
+
"num_negatives": 100,
|
63 |
+
"pad_token_id": 0,
|
64 |
+
"proj_codevector_dim": 256,
|
65 |
+
"tdnn_dilation": [
|
66 |
+
1,
|
67 |
+
1
|
68 |
+
],
|
69 |
+
"tdnn_dim": [
|
70 |
+
32,
|
71 |
+
32
|
72 |
+
],
|
73 |
+
"tdnn_kernel": [
|
74 |
+
3,
|
75 |
+
3
|
76 |
+
],
|
77 |
+
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.28.0.dev0",
|
79 |
+
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": 32,
|
81 |
+
"xvector_output_dim": 32
|
82 |
+
}
|
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": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e1f18c48d7f50793ceda62c4105bfdca6b6eefaa0cf0e38898881c6de809055
|
3 |
+
size 131806
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"do_normalize": true,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"replace_word_delimiter_char": " ",
|
10 |
+
"return_attention_mask": false,
|
11 |
+
"special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/6e305f345764752bb3b07ab4eaeebe722f895e6f1286d4821a76801f05282e5c.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd",
|
12 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
13 |
+
"tokenizer_file": null,
|
14 |
+
"unk_token": "<unk>",
|
15 |
+
"word_delimiter_token": "|"
|
16 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 27,
|
3 |
+
"</s>": 2,
|
4 |
+
"<pad>": 0,
|
5 |
+
"<s>": 1,
|
6 |
+
"<unk>": 3,
|
7 |
+
"A": 7,
|
8 |
+
"B": 24,
|
9 |
+
"C": 19,
|
10 |
+
"D": 14,
|
11 |
+
"E": 5,
|
12 |
+
"F": 20,
|
13 |
+
"G": 21,
|
14 |
+
"H": 11,
|
15 |
+
"I": 10,
|
16 |
+
"J": 29,
|
17 |
+
"K": 26,
|
18 |
+
"L": 15,
|
19 |
+
"M": 17,
|
20 |
+
"N": 9,
|
21 |
+
"O": 8,
|
22 |
+
"P": 23,
|
23 |
+
"Q": 30,
|
24 |
+
"R": 13,
|
25 |
+
"S": 12,
|
26 |
+
"T": 6,
|
27 |
+
"U": 16,
|
28 |
+
"V": 25,
|
29 |
+
"W": 18,
|
30 |
+
"X": 28,
|
31 |
+
"Y": 22,
|
32 |
+
"Z": 31,
|
33 |
+
"|": 4
|
34 |
+
}
|