Add model files for moroccan dialect
Browse files- config.json +9 -9
- pytorch_model.bin +3 -0
- vocab.json +1 -1
config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
-
"activation_dropout": 0.
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
7 |
],
|
8 |
-
"attention_dropout": 0.
|
9 |
"bos_token_id": 1,
|
10 |
"conv_bias": true,
|
11 |
"conv_dim": [
|
@@ -36,22 +36,22 @@
|
|
36 |
2
|
37 |
],
|
38 |
"ctc_loss_reduction": "mean",
|
39 |
-
"ctc_zero_infinity":
|
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.
|
46 |
"final_dropout": 0.0,
|
47 |
"gradient_checkpointing": true,
|
48 |
"hidden_act": "gelu",
|
49 |
-
"hidden_dropout": 0.
|
50 |
"hidden_size": 1024,
|
51 |
"initializer_range": 0.02,
|
52 |
"intermediate_size": 4096,
|
53 |
"layer_norm_eps": 1e-05,
|
54 |
-
"layerdrop": 0.
|
55 |
"mask_channel_length": 10,
|
56 |
"mask_channel_min_space": 1,
|
57 |
"mask_channel_other": 0.0,
|
@@ -62,7 +62,7 @@
|
|
62 |
"mask_time_length": 10,
|
63 |
"mask_time_min_space": 1,
|
64 |
"mask_time_other": 0.0,
|
65 |
-
"mask_time_prob": 0.
|
66 |
"mask_time_selection": "static",
|
67 |
"model_type": "wav2vec2",
|
68 |
"num_attention_heads": 16,
|
@@ -70,7 +70,7 @@
|
|
70 |
"num_conv_pos_embeddings": 128,
|
71 |
"num_feat_extract_layers": 7,
|
72 |
"num_hidden_layers": 24,
|
73 |
-
"pad_token_id":
|
74 |
"transformers_version": "4.4.0",
|
75 |
-
"vocab_size":
|
76 |
}
|
|
|
1 |
{
|
2 |
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
7 |
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
"bos_token_id": 1,
|
10 |
"conv_bias": true,
|
11 |
"conv_dim": [
|
|
|
36 |
2
|
37 |
],
|
38 |
"ctc_loss_reduction": "mean",
|
39 |
+
"ctc_zero_infinity": true,
|
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": 0.1,
|
46 |
"final_dropout": 0.0,
|
47 |
"gradient_checkpointing": true,
|
48 |
"hidden_act": "gelu",
|
49 |
+
"hidden_dropout": 0.1,
|
50 |
"hidden_size": 1024,
|
51 |
"initializer_range": 0.02,
|
52 |
"intermediate_size": 4096,
|
53 |
"layer_norm_eps": 1e-05,
|
54 |
+
"layerdrop": 0.0,
|
55 |
"mask_channel_length": 10,
|
56 |
"mask_channel_min_space": 1,
|
57 |
"mask_channel_other": 0.0,
|
|
|
62 |
"mask_time_length": 10,
|
63 |
"mask_time_min_space": 1,
|
64 |
"mask_time_other": 0.0,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
"mask_time_selection": "static",
|
67 |
"model_type": "wav2vec2",
|
68 |
"num_attention_heads": 16,
|
|
|
70 |
"num_conv_pos_embeddings": 128,
|
71 |
"num_feat_extract_layers": 7,
|
72 |
"num_hidden_layers": 24,
|
73 |
+
"pad_token_id": 64,
|
74 |
"transformers_version": "4.4.0",
|
75 |
+
"vocab_size": 65
|
76 |
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fd153384cafe5b830c62b09e80b7edcfbde38ad83f0f3b8de12de3fff2ec523
|
3 |
+
size 1262200343
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
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}
|