Erdene-Ochir Tuguldur
commited on
Commit
•
b6c6d48
1
Parent(s):
9cd752f
WER 51%
Browse files- config.json +14 -6
- preprocessor_config.json +1 -0
- pytorch_model.bin +2 -2
- vocab.json +1 -1
config.json
CHANGED
@@ -1,12 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation_dropout": 0.
|
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": [
|
12 |
512,
|
@@ -36,13 +38,15 @@
|
|
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": 0.0,
|
|
|
46 |
"final_dropout": 0.0,
|
47 |
"gradient_checkpointing": true,
|
48 |
"hidden_act": "gelu",
|
@@ -66,11 +70,15 @@
|
|
66 |
"mask_time_selection": "static",
|
67 |
"model_type": "wav2vec2",
|
68 |
"num_attention_heads": 16,
|
|
|
|
|
69 |
"num_conv_pos_embedding_groups": 16,
|
70 |
"num_conv_pos_embeddings": 128,
|
71 |
"num_feat_extract_layers": 7,
|
72 |
"num_hidden_layers": 24,
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"
|
|
|
|
|
76 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./xlsr",
|
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 |
+
"codevector_dim": 768,
|
11 |
+
"contrastive_logits_temperature": 0.1,
|
12 |
"conv_bias": true,
|
13 |
"conv_dim": [
|
14 |
512,
|
|
|
38 |
2
|
39 |
],
|
40 |
"ctc_loss_reduction": "mean",
|
41 |
+
"ctc_zero_infinity": true,
|
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": 0.0,
|
49 |
+
"feat_quantizer_dropout": 0.0,
|
50 |
"final_dropout": 0.0,
|
51 |
"gradient_checkpointing": true,
|
52 |
"hidden_act": "gelu",
|
|
|
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": 40,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
+
"transformers_version": "4.7.0",
|
83 |
+
"vocab_size": 41
|
84 |
}
|
preprocessor_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"do_normalize": true,
|
|
|
3 |
"feature_size": 1,
|
4 |
"padding_side": "right",
|
5 |
"padding_value": 0.0,
|
|
|
1 |
{
|
2 |
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71c8f04a7a2046ac58b1b41c693b0e330b00a8724a9108487922c1cf6bd006d3
|
3 |
+
size 1262091761
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"н": 0, "т": 1, "л": 2, "а": 3, "р": 4, "й": 5, "м": 6, "п": 7, "ө": 8, "ф": 9, "һ": 10, "ш": 11, "җ": 12, "о": 13, "в": 14, "ц": 15, "з": 16, "ә": 17, "и": 18, "э": 19, "к": 20, "ж": 21, "д": 22, "ъ": 23, "ь": 24, "е": 25, "ч": 26, "б": 27, "у": 28, "я": 30, "с": 31, "х": 32, "ы": 33, "г": 34, "ё": 35, "ң": 36, "ү": 37, "ю": 38, "|": 29, "[UNK]": 39, "[PAD]": 40}
|