Model save
Browse files- .gitignore +1 -0
- added_tokens.json +4 -0
- config.json +115 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Oct24_00-30-34_hieu-pc/1666546306.5224588/events.out.tfevents.1666546306.hieu-pc.1176500.1 +3 -0
- runs/Oct24_00-30-34_hieu-pc/events.out.tfevents.1666546306.hieu-pc.1176500.0 +3 -0
- runs/Oct24_00-39-40_hieu-pc/1666546845.2215862/events.out.tfevents.1666546845.hieu-pc.1202934.1 +3 -0
- runs/Oct24_00-39-40_hieu-pc/1666546953.3674529/events.out.tfevents.1666546953.hieu-pc.1202934.2 +3 -0
- runs/Oct24_00-39-40_hieu-pc/events.out.tfevents.1666546845.hieu-pc.1202934.0 +3 -0
- runs/Oct24_00-44-34_hieu-pc/1666547138.463529/events.out.tfevents.1666547138.hieu-pc.1221699.1 +3 -0
- runs/Oct24_00-44-34_hieu-pc/events.out.tfevents.1666547138.hieu-pc.1221699.0 +3 -0
- runs/Oct24_00-56-10_hieu-pc/1666547835.7066529/events.out.tfevents.1666547835.hieu-pc.1253338.1 +3 -0
- runs/Oct24_00-56-10_hieu-pc/events.out.tfevents.1666547835.hieu-pc.1253338.0 +3 -0
- runs/Oct24_01-00-20_hieu-pc/1666548083.8822463/events.out.tfevents.1666548083.hieu-pc.1270805.1 +3 -0
- runs/Oct24_01-00-20_hieu-pc/events.out.tfevents.1666548083.hieu-pc.1270805.0 +3 -0
- runs/Oct24_01-02-57_hieu-pc/1666548241.1635075/events.out.tfevents.1666548241.hieu-pc.1285597.1 +3 -0
- runs/Oct24_01-02-57_hieu-pc/events.out.tfevents.1666548241.hieu-pc.1285597.0 +3 -0
- runs/Oct24_21-14-33_hieu-pc/1666620939.1244476/events.out.tfevents.1666620939.hieu-pc.24974.1 +3 -0
- runs/Oct24_21-14-33_hieu-pc/events.out.tfevents.1666620939.hieu-pc.24974.0 +3 -0
- runs/Oct24_21-27-24_hieu-pc/1666621707.5945218/events.out.tfevents.1666621707.hieu-pc.55372.1 +3 -0
- runs/Oct24_21-27-24_hieu-pc/events.out.tfevents.1666621707.hieu-pc.55372.0 +3 -0
- runs/Oct24_21-38-25_hieu-pc/1666622369.6698897/events.out.tfevents.1666622369.hieu-pc.82206.1 +3 -0
- runs/Oct24_21-38-25_hieu-pc/events.out.tfevents.1666622369.hieu-pc.82206.0 +3 -0
- special_tokens_map.json +134 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
- vocab.json +93 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 92,
|
3 |
+
"<s>": 91
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
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 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 1024,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 4096,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"layerdrop": 0.0,
|
62 |
+
"mask_channel_length": 10,
|
63 |
+
"mask_channel_min_space": 1,
|
64 |
+
"mask_channel_other": 0.0,
|
65 |
+
"mask_channel_prob": 0.0,
|
66 |
+
"mask_channel_selection": "static",
|
67 |
+
"mask_feature_length": 10,
|
68 |
+
"mask_feature_min_masks": 0,
|
69 |
+
"mask_feature_prob": 0.0,
|
70 |
+
"mask_time_length": 10,
|
71 |
+
"mask_time_min_masks": 2,
|
72 |
+
"mask_time_min_space": 1,
|
73 |
+
"mask_time_other": 0.0,
|
74 |
+
"mask_time_prob": 0.05,
|
75 |
+
"mask_time_selection": "static",
|
76 |
+
"model_type": "wav2vec2",
|
77 |
+
"num_adapter_layers": 3,
|
78 |
+
"num_attention_heads": 16,
|
79 |
+
"num_codevector_groups": 2,
|
80 |
+
"num_codevectors_per_group": 320,
|
81 |
+
"num_conv_pos_embedding_groups": 16,
|
82 |
+
"num_conv_pos_embeddings": 128,
|
83 |
+
"num_feat_extract_layers": 7,
|
84 |
+
"num_hidden_layers": 24,
|
85 |
+
"num_negatives": 100,
|
86 |
+
"output_hidden_size": 1024,
|
87 |
+
"pad_token_id": 90,
|
88 |
+
"proj_codevector_dim": 768,
|
89 |
+
"tdnn_dilation": [
|
90 |
+
1,
|
91 |
+
2,
|
92 |
+
3,
|
93 |
+
1,
|
94 |
+
1
|
95 |
+
],
|
96 |
+
"tdnn_dim": [
|
97 |
+
512,
|
98 |
+
512,
|
99 |
+
512,
|
100 |
+
512,
|
101 |
+
1500
|
102 |
+
],
|
103 |
+
"tdnn_kernel": [
|
104 |
+
5,
|
105 |
+
3,
|
106 |
+
3,
|
107 |
+
1,
|
108 |
+
1
|
109 |
+
],
|
110 |
+
"torch_dtype": "float32",
|
111 |
+
"transformers_version": "4.23.1",
|
112 |
+
"use_weighted_layer_sum": false,
|
113 |
+
"vocab_size": 93,
|
114 |
+
"xvector_output_dim": 512
|
115 |
+
}
|
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": 48000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9057c1a4249bf51c461b0a564c26080fc37e344222e000f9dfa3fbb5ff4e3f12
|
3 |
+
size 1262274097
|
runs/Oct24_00-30-34_hieu-pc/1666546306.5224588/events.out.tfevents.1666546306.hieu-pc.1176500.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:348d2c16f3c8d44e10b219922c7b68c3d55ecde2885ede7ef5ea7f90d0f6ffe3
|
3 |
+
size 5503
|
runs/Oct24_00-30-34_hieu-pc/events.out.tfevents.1666546306.hieu-pc.1176500.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1b8779862a9412a4380bfef8e18110cf3205e17930311164f5088ce8a742ebd
|
3 |
+
size 5338
|
runs/Oct24_00-39-40_hieu-pc/1666546845.2215862/events.out.tfevents.1666546845.hieu-pc.1202934.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4f3bcf0fe2b9c3bbd63feacf5247fb7acf8a878eafe2cc8617de9764728e981
|
3 |
+
size 5503
|
runs/Oct24_00-39-40_hieu-pc/1666546953.3674529/events.out.tfevents.1666546953.hieu-pc.1202934.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9344cb7a7e1e293bfbe8a1eee3611ab7c8db5ea85d5a74575e5097b46f557f4c
|
3 |
+
size 5503
|
runs/Oct24_00-39-40_hieu-pc/events.out.tfevents.1666546845.hieu-pc.1202934.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae94a36756237fd4586ba3d5fb055a83b7e2c240283033840893e9d2906ea35c
|
3 |
+
size 10634
|
runs/Oct24_00-44-34_hieu-pc/1666547138.463529/events.out.tfevents.1666547138.hieu-pc.1221699.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb60b99e1d28dc7a8b1360df8e8d720756bf121c7838d1a98fefbaa9443fbe6f
|
3 |
+
size 5503
|
runs/Oct24_00-44-34_hieu-pc/events.out.tfevents.1666547138.hieu-pc.1221699.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9e386afa9c3d063388ff6b2d2f97cf52201fa0e6f6238e0c6f82c2beda99840
|
3 |
+
size 5338
|
runs/Oct24_00-56-10_hieu-pc/1666547835.7066529/events.out.tfevents.1666547835.hieu-pc.1253338.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7cc96e8ec1ef015d720e8e671344d3fa51f53e310cab53b008488a4e1af2899
|
3 |
+
size 5503
|
runs/Oct24_00-56-10_hieu-pc/events.out.tfevents.1666547835.hieu-pc.1253338.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74bf9d9413000b64b9274aa03faf2632268e7622ea44acce5c84c0c19911ce29
|
3 |
+
size 5337
|
runs/Oct24_01-00-20_hieu-pc/1666548083.8822463/events.out.tfevents.1666548083.hieu-pc.1270805.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad9a526a1e57c1add61208be21220ce9ccf651ce214d33e395636012e833f34
|
3 |
+
size 5503
|
runs/Oct24_01-00-20_hieu-pc/events.out.tfevents.1666548083.hieu-pc.1270805.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a66d1c930cccc8eac7bd6fcab14b126a1699b28e1fdae0b696f68d75ca4cb7bf
|
3 |
+
size 5337
|
runs/Oct24_01-02-57_hieu-pc/1666548241.1635075/events.out.tfevents.1666548241.hieu-pc.1285597.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a71051a368aa9bffc8d8d3161be32009e1bf154d859ac5cda89b48b9ea18af
|
3 |
+
size 5503
|
runs/Oct24_01-02-57_hieu-pc/events.out.tfevents.1666548241.hieu-pc.1285597.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37013a921cf4e6b0d55b3383ebacca385531234b702b02c037c36f7eeea0920b
|
3 |
+
size 5337
|
runs/Oct24_21-14-33_hieu-pc/1666620939.1244476/events.out.tfevents.1666620939.hieu-pc.24974.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeae467c876efb29107cbeea07783269e258257810fd40ce54c01493fe58f165
|
3 |
+
size 5499
|
runs/Oct24_21-14-33_hieu-pc/events.out.tfevents.1666620939.hieu-pc.24974.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9591b03b1542748a59ac085d052ea9330892b5212ca46a40947bb7b4f2168b4
|
3 |
+
size 5333
|
runs/Oct24_21-27-24_hieu-pc/1666621707.5945218/events.out.tfevents.1666621707.hieu-pc.55372.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10511c6162add351f5fb6d6a2cfbd3c6dccd8520b4569824e89c8e18bba2f094
|
3 |
+
size 5499
|
runs/Oct24_21-27-24_hieu-pc/events.out.tfevents.1666621707.hieu-pc.55372.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d726c65054843dacae82c0bde89186ee1e1a0845b53ca319bc6d1efaa48862c
|
3 |
+
size 5333
|
runs/Oct24_21-38-25_hieu-pc/1666622369.6698897/events.out.tfevents.1666622369.hieu-pc.82206.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21e41b9b44230b742a1d0586c47f2eb3fcf16a4b3a3ff983c3d979f5efedf70
|
3 |
+
size 5499
|
runs/Oct24_21-38-25_hieu-pc/events.out.tfevents.1666622369.hieu-pc.82206.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dec5fe1b9801c41768b790a7c6359f383c0edf095a7fd1b232753ebbc0c11c64
|
3 |
+
size 6001
|
special_tokens_map.json
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<s>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "</s>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<s>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "</s>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<s>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "</s>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"content": "<s>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"content": "</s>",
|
68 |
+
"lstrip": false,
|
69 |
+
"normalized": true,
|
70 |
+
"rstrip": false,
|
71 |
+
"single_word": false
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"content": "<s>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": true,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"content": "</s>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": true,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"content": "<s>",
|
89 |
+
"lstrip": false,
|
90 |
+
"normalized": true,
|
91 |
+
"rstrip": false,
|
92 |
+
"single_word": false
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"content": "</s>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"content": "<s>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": true,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"content": "</s>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"content": "<s>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"content": "</s>",
|
124 |
+
"lstrip": false,
|
125 |
+
"normalized": true,
|
126 |
+
"rstrip": false,
|
127 |
+
"single_word": false
|
128 |
+
}
|
129 |
+
],
|
130 |
+
"bos_token": "<s>",
|
131 |
+
"eos_token": "</s>",
|
132 |
+
"pad_token": "[PAD]",
|
133 |
+
"unk_token": "[UNK]"
|
134 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"name_or_path": "./wav2vec2-common_voice-vi",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"replace_word_delimiter_char": " ",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
10 |
+
"unk_token": "[UNK]",
|
11 |
+
"word_delimiter_token": "|"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:783a50a30f8f1ce621ba4e62925ad56267c1512d15d68f6eae62078a7ae2703b
|
3 |
+
size 3375
|
vocab.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 90,
|
3 |
+
"[UNK]": 89,
|
4 |
+
"a": 68,
|
5 |
+
"b": 30,
|
6 |
+
"c": 15,
|
7 |
+
"d": 35,
|
8 |
+
"e": 62,
|
9 |
+
"g": 73,
|
10 |
+
"h": 18,
|
11 |
+
"i": 23,
|
12 |
+
"k": 79,
|
13 |
+
"l": 31,
|
14 |
+
"m": 3,
|
15 |
+
"n": 40,
|
16 |
+
"o": 49,
|
17 |
+
"p": 32,
|
18 |
+
"q": 48,
|
19 |
+
"r": 38,
|
20 |
+
"s": 86,
|
21 |
+
"t": 17,
|
22 |
+
"u": 80,
|
23 |
+
"v": 39,
|
24 |
+
"x": 69,
|
25 |
+
"y": 29,
|
26 |
+
"|": 53,
|
27 |
+
"à": 9,
|
28 |
+
"á": 50,
|
29 |
+
"â": 45,
|
30 |
+
"ã": 59,
|
31 |
+
"è": 67,
|
32 |
+
"é": 52,
|
33 |
+
"ê": 43,
|
34 |
+
"ì": 51,
|
35 |
+
"í": 63,
|
36 |
+
"ò": 85,
|
37 |
+
"ó": 46,
|
38 |
+
"ô": 57,
|
39 |
+
"õ": 58,
|
40 |
+
"ù": 7,
|
41 |
+
"ú": 33,
|
42 |
+
"ý": 81,
|
43 |
+
"ă": 10,
|
44 |
+
"đ": 41,
|
45 |
+
"ĩ": 8,
|
46 |
+
"ũ": 82,
|
47 |
+
"ơ": 1,
|
48 |
+
"ư": 56,
|
49 |
+
"ạ": 84,
|
50 |
+
"ả": 5,
|
51 |
+
"ấ": 12,
|
52 |
+
"ầ": 4,
|
53 |
+
"ẩ": 42,
|
54 |
+
"ẫ": 16,
|
55 |
+
"ậ": 14,
|
56 |
+
"ắ": 36,
|
57 |
+
"ằ": 20,
|
58 |
+
"ẳ": 37,
|
59 |
+
"ẵ": 6,
|
60 |
+
"ặ": 44,
|
61 |
+
"ẹ": 72,
|
62 |
+
"ẻ": 78,
|
63 |
+
"ẽ": 21,
|
64 |
+
"ế": 54,
|
65 |
+
"ề": 64,
|
66 |
+
"ể": 75,
|
67 |
+
"ễ": 28,
|
68 |
+
"ệ": 71,
|
69 |
+
"ỉ": 61,
|
70 |
+
"ị": 65,
|
71 |
+
"ọ": 47,
|
72 |
+
"ỏ": 88,
|
73 |
+
"ố": 11,
|
74 |
+
"ồ": 76,
|
75 |
+
"ổ": 83,
|
76 |
+
"ỗ": 70,
|
77 |
+
"ộ": 0,
|
78 |
+
"ớ": 22,
|
79 |
+
"ờ": 77,
|
80 |
+
"ở": 74,
|
81 |
+
"ỡ": 27,
|
82 |
+
"ợ": 60,
|
83 |
+
"ụ": 55,
|
84 |
+
"ủ": 66,
|
85 |
+
"ứ": 19,
|
86 |
+
"ừ": 34,
|
87 |
+
"ử": 13,
|
88 |
+
"ữ": 25,
|
89 |
+
"ự": 2,
|
90 |
+
"ỳ": 24,
|
91 |
+
"ỷ": 87,
|
92 |
+
"ỹ": 26
|
93 |
+
}
|