Martijn Bartelds commited on
Commit
c65213a
1 Parent(s): c849d0e

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: nl
3
+ tags:
4
+ - speech
5
+ ---
6
+
7
+ # Wav2Vec2-Large-XLSR-53-ft-CGN
8
+
9
+ This model is created by fine-tuning the [`facebook/wav2vec2-large-xlsr-53`](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) model on Dutch speech from [Het Corpus Gesproken Nederlands](https://taalmaterialen.ivdnt.org/download/tstc-corpus-gesproken-nederlands/) using CTC.
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "classifier_proj_size": 256,
10
+ "codevector_dim": 768,
11
+ "contrastive_logits_temperature": 0.1,
12
+ "conv_bias": true,
13
+ "conv_dim": [
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "conv_kernel": [
23
+ 10,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2
30
+ ],
31
+ "conv_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "sum",
41
+ "ctc_zero_infinity": false,
42
+ "diversity_loss_weight": 0.1,
43
+ "do_stable_layer_norm": true,
44
+ "eos_token_id": 2,
45
+ "feat_extract_activation": "gelu",
46
+ "feat_extract_dropout": 0.0,
47
+ "feat_extract_norm": "layer",
48
+ "feat_proj_dropout": 0.1,
49
+ "feat_quantizer_dropout": 0.0,
50
+ "final_dropout": 0.0,
51
+ "gradient_checkpointing": false,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.1,
54
+ "hidden_size": 1024,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 4096,
57
+ "layer_norm_eps": 1e-05,
58
+ "layerdrop": 0.1,
59
+ "mask_channel_length": 10,
60
+ "mask_channel_min_space": 1,
61
+ "mask_channel_other": 0.0,
62
+ "mask_channel_prob": 0.0,
63
+ "mask_channel_selection": "static",
64
+ "mask_feature_length": 10,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_space": 1,
68
+ "mask_time_other": 0.0,
69
+ "mask_time_prob": 0.075,
70
+ "mask_time_selection": "static",
71
+ "model_type": "wav2vec2",
72
+ "num_attention_heads": 16,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 24,
79
+ "num_negatives": 100,
80
+ "pad_token_id": 0,
81
+ "proj_codevector_dim": 768,
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.11.1",
84
+ "use_weighted_layer_sum": false,
85
+ "vocab_size": 37
86
+ }
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
+ }
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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "A": 5, "B": 6, "C": 7, "D": 8, "E": 9, "F": 10, "G": 11, "H": 12, "I": 13, "J": 14, "K": 15, "L": 16, "M": 17, "N": 18, "O": 19, "P": 20, "Q": 21, "R": 22, "S": 23, "T": 24, "U": 25, "V": 26, "W": 27, "X": 28, "Y": 29, "Z": 30, "È": 31, "É": 32, "Ë": 33, "?": 34, "'": 35, "-": 36}