Upload 4 files
Browse files
wav2vec2-large-xlsr-moroccan-darija/config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "C:\\workspace\\checkpoints\\",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForCTC"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 768,
|
15 |
+
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": true,
|
17 |
+
"conv_dim": [
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512
|
25 |
+
],
|
26 |
+
"conv_kernel": [
|
27 |
+
10,
|
28 |
+
3,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
2,
|
33 |
+
2
|
34 |
+
],
|
35 |
+
"conv_stride": [
|
36 |
+
5,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2
|
43 |
+
],
|
44 |
+
"ctc_loss_reduction": "mean",
|
45 |
+
"ctc_zero_infinity": false,
|
46 |
+
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": true,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "layer",
|
52 |
+
"feat_proj_dropout": 0.0,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.0,
|
58 |
+
"hidden_size": 1024,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 4096,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
63 |
+
"mask_channel_length": 10,
|
64 |
+
"mask_channel_min_space": 1,
|
65 |
+
"mask_channel_other": 0.0,
|
66 |
+
"mask_channel_prob": 0.0,
|
67 |
+
"mask_channel_selection": "static",
|
68 |
+
"mask_feature_length": 10,
|
69 |
+
"mask_feature_min_masks": 0,
|
70 |
+
"mask_feature_prob": 0.0,
|
71 |
+
"mask_time_length": 10,
|
72 |
+
"mask_time_min_masks": 2,
|
73 |
+
"mask_time_min_space": 1,
|
74 |
+
"mask_time_other": 0.0,
|
75 |
+
"mask_time_prob": 0.05,
|
76 |
+
"mask_time_selection": "static",
|
77 |
+
"model_type": "wav2vec2",
|
78 |
+
"num_adapter_layers": 3,
|
79 |
+
"num_attention_heads": 16,
|
80 |
+
"num_codevector_groups": 2,
|
81 |
+
"num_codevectors_per_group": 320,
|
82 |
+
"num_conv_pos_embedding_groups": 16,
|
83 |
+
"num_conv_pos_embeddings": 128,
|
84 |
+
"num_feat_extract_layers": 7,
|
85 |
+
"num_hidden_layers": 24,
|
86 |
+
"num_negatives": 100,
|
87 |
+
"output_hidden_size": 1024,
|
88 |
+
"pad_token_id": 64,
|
89 |
+
"proj_codevector_dim": 768,
|
90 |
+
"tdnn_dilation": [
|
91 |
+
1,
|
92 |
+
2,
|
93 |
+
3,
|
94 |
+
1,
|
95 |
+
1
|
96 |
+
],
|
97 |
+
"tdnn_dim": [
|
98 |
+
512,
|
99 |
+
512,
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
1500
|
103 |
+
],
|
104 |
+
"tdnn_kernel": [
|
105 |
+
5,
|
106 |
+
3,
|
107 |
+
3,
|
108 |
+
1,
|
109 |
+
1
|
110 |
+
],
|
111 |
+
"torch_dtype": "float32",
|
112 |
+
"transformers_version": "4.21.1",
|
113 |
+
"use_weighted_layer_sum": false,
|
114 |
+
"vocab_size": 65,
|
115 |
+
"xvector_output_dim": 512
|
116 |
+
}
|
wav2vec2-large-xlsr-moroccan-darija/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": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
wav2vec2-large-xlsr-moroccan-darija/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": "|"}
|
wav2vec2-large-xlsr-moroccan-darija/vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ا": 0, "_": 1, "ك": 3, "ن": 4, "@": 5, "ذ": 6, "ٖ": 7, "ش": 8, "غ": 9, "آ": 10, "ص": 11, "ي": 12, "ث": 13, "n": 14, "ج": 15, "d": 16, "ئ": 17, "ة": 18, "ه": 19, "ز": 20, "ع": 21, "ف": 22, "i": 23, "r": 24, "v": 25, "ڸ": 26, "k": 27, "ِ": 28, "ء": 29, "ر": 30, "s": 31, "t": 32, "ى": 33, "ـ": 34, " ": 35, "ؤ": 36, "ق": 37, "ض": 38, "م": 39, "ل": 40, "…": 41, "ط": 42, "ت": 43, "ّ": 44, "c": 45, "ظ": 46, "e": 47, "؟": 48, "h": 49, "ب": 50, "o": 51, "س": 52, "a": 53, "د": 54, "p": 55, "أ": 56, "ْ": 57, "\n": 58, "خ": 59, "ح": 60, "و": 61, "إ": 62, "|": 2, "[UNK]": 63, "[PAD]": 64}
|