chipewyan
commited on
Commit
•
93b4684
1
Parent(s):
72abe0d
model upload
Browse files- wav2vec2-large-xlsr-japlmthufielta-ipa2000/config.json +116 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/preprocessor_config.json +9 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/pytorch_model.bin +3 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/special_tokens_map.json +6 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/tokenizer_config.json +11 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/upload.py +38 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/vocab.json +315 -0
- wav2vec2-large-xlsr-japlmthufielta-ipa2000/vocab_ipa_full.json +1 -0
wav2vec2-large-xlsr-japlmthufielta-ipa2000/config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./",
|
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": 0.1,
|
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": 0.1,
|
58 |
+
"hidden_size": 1024,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 4096,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.1,
|
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": 312,
|
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": "4.26.0.dev0",
|
113 |
+
"use_weighted_layer_sum": false,
|
114 |
+
"vocab_size": 313,
|
115 |
+
"xvector_output_dim": 512
|
116 |
+
}
|
wav2vec2-large-xlsr-japlmthufielta-ipa2000/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-japlmthufielta-ipa2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2b97efffa6037cae3abd7dff36e79637da33662bf91e407d57d9cdfa6cfe128
|
3 |
+
size 1263179245
|
wav2vec2-large-xlsr-japlmthufielta-ipa2000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
wav2vec2-large-xlsr-japlmthufielta-ipa2000/tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"replace_word_delimiter_char": " ",
|
8 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
9 |
+
"unk_token": "[UNK]",
|
10 |
+
"word_delimiter_token": "|"
|
11 |
+
}
|
wav2vec2-large-xlsr-japlmthufielta-ipa2000/upload.py
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import Wav2Vec2CTCTokenizer, Wav2Vec2FeatureExtractor, Wav2Vec2Processor, Wav2Vec2ForCTC, TrainingArguments, Trainer
|
2 |
+
import argparse
|
3 |
+
|
4 |
+
def upload(model_path, vocab_file, directory):
|
5 |
+
"""
|
6 |
+
Running this function will create additional necessary files such as `special_tokens_map.json`
|
7 |
+
and make it ready for the model to be uploaded on the huggingface repository.
|
8 |
+
"""
|
9 |
+
|
10 |
+
print("Reading the model...")
|
11 |
+
model = Wav2Vec2ForCTC.from_pretrained(model_path)
|
12 |
+
print("Model read")
|
13 |
+
|
14 |
+
print("Reading the tokenizer...")
|
15 |
+
tokenizer_sentence = Wav2Vec2CTCTokenizer("./{}".format(vocab_file), unk_token="[UNK]",
|
16 |
+
pad_token="[PAD]", word_delimiter_token="|")
|
17 |
+
print("Tokenizer read")
|
18 |
+
|
19 |
+
print("Saving the model...")
|
20 |
+
model.save_pretrained(directory)
|
21 |
+
print("Model saved")
|
22 |
+
print("Saving the tokenizer...")
|
23 |
+
tokenizer_sentence.save_pretrained(directory)
|
24 |
+
print("Tokenizer saved")
|
25 |
+
|
26 |
+
if __name__ == "__main__":
|
27 |
+
parser = argparse.ArgumentParser()
|
28 |
+
parser.add_argument("-m", "--model_path", default="./", type=str,
|
29 |
+
help="Model (checkpoint) directory path")
|
30 |
+
parser.add_argument("-v", "--vocab_file", required=True, type=str,
|
31 |
+
help="Vocab file path")
|
32 |
+
parser.add_argument("-d", "--directory", default="./", type=str,
|
33 |
+
help="Destination of the saved model")
|
34 |
+
args = parser.parse_args()
|
35 |
+
model_path = args.model_path
|
36 |
+
vocab_file = args.vocab_file
|
37 |
+
directory = args.directory
|
38 |
+
upload(model_path, vocab_file, directory)
|
wav2vec2-large-xlsr-japlmthufielta-ipa2000/vocab.json
ADDED
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 207,
|
3 |
+
"#": 15,
|
4 |
+
"'": 85,
|
5 |
+
"[PAD]": 312,
|
6 |
+
"[UNK]": 311,
|
7 |
+
"a": 243,
|
8 |
+
"ã": 62,
|
9 |
+
"b": 16,
|
10 |
+
"b̪": 60,
|
11 |
+
"b̪͡v": 304,
|
12 |
+
"b͡ꞵ": 278,
|
13 |
+
"c": 292,
|
14 |
+
"cʼ": 209,
|
15 |
+
"c͡ç": 26,
|
16 |
+
"d": 215,
|
17 |
+
"d̼": 159,
|
18 |
+
"d͡z": 307,
|
19 |
+
"d͡ð": 161,
|
20 |
+
"d͡ɮ": 126,
|
21 |
+
"d͡ʑ": 105,
|
22 |
+
"d͡ʒ": 217,
|
23 |
+
"e": 53,
|
24 |
+
"ẽ": 116,
|
25 |
+
"e̞": 150,
|
26 |
+
"ẽ̞": 282,
|
27 |
+
"f": 135,
|
28 |
+
"fʼ": 100,
|
29 |
+
"g": 192,
|
30 |
+
"h": 102,
|
31 |
+
"i": 277,
|
32 |
+
"j": 174,
|
33 |
+
"k": 244,
|
34 |
+
"kxʼ": 214,
|
35 |
+
"kǀ": 134,
|
36 |
+
"kǁ": 3,
|
37 |
+
"kǂ": 54,
|
38 |
+
"kǃ": 131,
|
39 |
+
"kʘ": 227,
|
40 |
+
"kʼ": 141,
|
41 |
+
"k̚": 83,
|
42 |
+
"k͡p": 57,
|
43 |
+
"k͡x": 87,
|
44 |
+
"l": 45,
|
45 |
+
"m": 250,
|
46 |
+
"m̥": 229,
|
47 |
+
"n": 193,
|
48 |
+
"n̥": 66,
|
49 |
+
"n̼": 118,
|
50 |
+
"o": 294,
|
51 |
+
"õ": 39,
|
52 |
+
"o̞": 50,
|
53 |
+
"õ̞": 224,
|
54 |
+
"p": 73,
|
55 |
+
"pʼ": 144,
|
56 |
+
"p̚": 293,
|
57 |
+
"p̪": 86,
|
58 |
+
"p̪͡f": 187,
|
59 |
+
"p͡f": 103,
|
60 |
+
"p͡ɸ": 183,
|
61 |
+
"q": 124,
|
62 |
+
"qǀ": 180,
|
63 |
+
"qǁ": 286,
|
64 |
+
"qǂ": 188,
|
65 |
+
"qǃ": 210,
|
66 |
+
"qʘ": 82,
|
67 |
+
"qʼ": 88,
|
68 |
+
"q͡ʡ": 247,
|
69 |
+
"q͡χʼ": 189,
|
70 |
+
"q͡ꭓ": 93,
|
71 |
+
"r": 163,
|
72 |
+
"r̥": 287,
|
73 |
+
"s": 34,
|
74 |
+
"sʼ": 72,
|
75 |
+
"t": 47,
|
76 |
+
"tʼ": 228,
|
77 |
+
"t̚": 7,
|
78 |
+
"t̪͡θʼ": 291,
|
79 |
+
"t̼": 197,
|
80 |
+
"t͡s": 0,
|
81 |
+
"t͡sʼ": 89,
|
82 |
+
"t͡ɕ": 258,
|
83 |
+
"t͡ɬ": 165,
|
84 |
+
"t͡ɬʼ": 213,
|
85 |
+
"t͡ʃ": 91,
|
86 |
+
"t͡ʃʼ": 279,
|
87 |
+
"t͡θ": 18,
|
88 |
+
"u": 200,
|
89 |
+
"ũ": 296,
|
90 |
+
"v": 202,
|
91 |
+
"w": 104,
|
92 |
+
"x": 190,
|
93 |
+
"xʼ": 284,
|
94 |
+
"y": 151,
|
95 |
+
"ỹ": 84,
|
96 |
+
"z": 8,
|
97 |
+
"á": 113,
|
98 |
+
"ä": 96,
|
99 |
+
"ä̃": 157,
|
100 |
+
"æ": 140,
|
101 |
+
"æ̃": 256,
|
102 |
+
"ç": 166,
|
103 |
+
"é": 225,
|
104 |
+
"ð": 147,
|
105 |
+
"ð̠": 42,
|
106 |
+
"ð̼": 30,
|
107 |
+
"ø": 283,
|
108 |
+
"ø̃": 107,
|
109 |
+
"ø̞": 79,
|
110 |
+
"ø̞̃": 132,
|
111 |
+
"ħ": 199,
|
112 |
+
"ŋ": 56,
|
113 |
+
"ŋǀ": 6,
|
114 |
+
"ŋǁ": 241,
|
115 |
+
"ŋǂ": 290,
|
116 |
+
"ŋǃ": 43,
|
117 |
+
"ŋʘ": 251,
|
118 |
+
"ŋ̊": 171,
|
119 |
+
"ŋ͡m": 309,
|
120 |
+
"œ": 97,
|
121 |
+
"œ̃": 40,
|
122 |
+
"ǀ": 41,
|
123 |
+
"ǃ": 168,
|
124 |
+
"ɐ": 300,
|
125 |
+
"ɐ̃": 61,
|
126 |
+
"ɑ": 220,
|
127 |
+
"ɑ̃": 108,
|
128 |
+
"ɒ": 70,
|
129 |
+
"ɒ̃": 196,
|
130 |
+
"ɓ": 295,
|
131 |
+
"ɓ̥": 49,
|
132 |
+
"ɔ": 12,
|
133 |
+
"ɔ̃": 275,
|
134 |
+
"ɕ": 17,
|
135 |
+
"ɕʼ": 14,
|
136 |
+
"ɖ": 248,
|
137 |
+
"ɖ͡ʐ": 191,
|
138 |
+
"ɗ": 233,
|
139 |
+
"ɗ̥": 201,
|
140 |
+
"ɘ": 160,
|
141 |
+
"ɘ̃": 99,
|
142 |
+
"ə": 164,
|
143 |
+
"ə̃": 156,
|
144 |
+
"ɚ": 75,
|
145 |
+
"ɛ": 184,
|
146 |
+
"ɛ̃": 58,
|
147 |
+
"ɜ": 55,
|
148 |
+
"ɜ̃": 22,
|
149 |
+
"ɝ": 38,
|
150 |
+
"ɞ": 212,
|
151 |
+
"ɞ̃": 221,
|
152 |
+
"ɟ": 194,
|
153 |
+
"ɟ͡ʝ": 143,
|
154 |
+
"ɠ": 95,
|
155 |
+
"ɠ̊": 65,
|
156 |
+
"ɡ": 71,
|
157 |
+
"ɡǀ": 123,
|
158 |
+
"ɡǁ": 31,
|
159 |
+
"ɡǂ": 21,
|
160 |
+
"ɡǃ": 92,
|
161 |
+
"ɡʘ": 281,
|
162 |
+
"ɡ̆": 2,
|
163 |
+
"ɡ͡b": 81,
|
164 |
+
"ɡ͡ɣ": 252,
|
165 |
+
"ɢ": 259,
|
166 |
+
"ɢǀ": 198,
|
167 |
+
"ɢǁ": 265,
|
168 |
+
"ɢǂ": 246,
|
169 |
+
"ɢǃ": 177,
|
170 |
+
"ɢʘ": 195,
|
171 |
+
"ɢ̆": 10,
|
172 |
+
"ɢ͡ʁ": 172,
|
173 |
+
"ɣ": 267,
|
174 |
+
"ɤ": 115,
|
175 |
+
"ɤ̃": 98,
|
176 |
+
"ɤ̞": 175,
|
177 |
+
"ɤ̞̃": 120,
|
178 |
+
"ɥ": 268,
|
179 |
+
"ɥ̊": 264,
|
180 |
+
"ɧ": 238,
|
181 |
+
"ɨ": 260,
|
182 |
+
"ɨ̃": 64,
|
183 |
+
"ɪ": 19,
|
184 |
+
"ɪ̃": 216,
|
185 |
+
"ɬ": 205,
|
186 |
+
"ɬʼ": 27,
|
187 |
+
"ɭ": 245,
|
188 |
+
"ɭ˔": 232,
|
189 |
+
"ɭ̆": 211,
|
190 |
+
"ɭ̥̆": 254,
|
191 |
+
"ɮ": 169,
|
192 |
+
"ɯ": 280,
|
193 |
+
"ɯ̃": 230,
|
194 |
+
"ɰ": 29,
|
195 |
+
"ɱ": 59,
|
196 |
+
"ɲ": 20,
|
197 |
+
"ɲ̊": 130,
|
198 |
+
"ɳ": 128,
|
199 |
+
"ɳ̊": 5,
|
200 |
+
"ɴ": 167,
|
201 |
+
"ɴǀ": 36,
|
202 |
+
"ɴǁ": 272,
|
203 |
+
"ɴǂ": 236,
|
204 |
+
"ɴǃ": 106,
|
205 |
+
"ɴʘ": 262,
|
206 |
+
"ɵ": 109,
|
207 |
+
"ɵ̃": 231,
|
208 |
+
"ɶ": 33,
|
209 |
+
"ɶ̃": 127,
|
210 |
+
"ɸ": 289,
|
211 |
+
"ɸʼ": 67,
|
212 |
+
"ɹ": 222,
|
213 |
+
"ɹ̠˔": 51,
|
214 |
+
"ɹ̠̊˔": 13,
|
215 |
+
"ɺ": 1,
|
216 |
+
"ɺ̥": 153,
|
217 |
+
"ɻ": 170,
|
218 |
+
"ɻ˔": 271,
|
219 |
+
"ɻ̊˔": 136,
|
220 |
+
"ɽ": 249,
|
221 |
+
"ɽ̊": 206,
|
222 |
+
"ɾ": 186,
|
223 |
+
"ɾ̥": 133,
|
224 |
+
"ɾ̼": 4,
|
225 |
+
"ʀ": 35,
|
226 |
+
"ʀ̥": 242,
|
227 |
+
"ʁ": 204,
|
228 |
+
"ʂ": 23,
|
229 |
+
"ʂʼ": 266,
|
230 |
+
"ʃ": 185,
|
231 |
+
"ʃʼ": 111,
|
232 |
+
"ʄ": 253,
|
233 |
+
"ʄ̊": 78,
|
234 |
+
"ʈ": 218,
|
235 |
+
"ʈʼ": 112,
|
236 |
+
"ʈ͡ʂ": 273,
|
237 |
+
"ʈ͡ʂʼ": 179,
|
238 |
+
"ʉ": 119,
|
239 |
+
"ʉ̃": 90,
|
240 |
+
"ʊ": 239,
|
241 |
+
"ʊ̃": 182,
|
242 |
+
"ʋ": 208,
|
243 |
+
"ʌ": 37,
|
244 |
+
"ʌ̃": 129,
|
245 |
+
"ʍ": 288,
|
246 |
+
"ʎ": 32,
|
247 |
+
"ʎ̆": 137,
|
248 |
+
"ʎ̝": 117,
|
249 |
+
"ʎ̝̊": 203,
|
250 |
+
"ʏ": 240,
|
251 |
+
"ʏ̃": 176,
|
252 |
+
"ʐ": 63,
|
253 |
+
"ʑ": 226,
|
254 |
+
"ʒ": 146,
|
255 |
+
"ʔ": 235,
|
256 |
+
"ʔ̞": 269,
|
257 |
+
"ʔ͡h": 173,
|
258 |
+
"ʕ": 52,
|
259 |
+
"ʙ": 301,
|
260 |
+
"ʙ̥": 299,
|
261 |
+
"ʛ": 121,
|
262 |
+
"ʛ̥": 9,
|
263 |
+
"ʜ": 155,
|
264 |
+
"ʝ": 303,
|
265 |
+
"ʟ": 158,
|
266 |
+
"ʟ̆": 237,
|
267 |
+
"ʟ̝": 28,
|
268 |
+
"ʟ̝̊": 145,
|
269 |
+
"ʟ̠": 302,
|
270 |
+
"ʡ": 25,
|
271 |
+
"ʡʼ": 234,
|
272 |
+
"ʡ̆": 74,
|
273 |
+
"ʡ͡ʜ": 219,
|
274 |
+
"ʡ͡ʢ": 306,
|
275 |
+
"ʢ": 274,
|
276 |
+
"ʰ": 181,
|
277 |
+
"ʲ": 154,
|
278 |
+
"ʷ": 80,
|
279 |
+
"ʼ": 285,
|
280 |
+
"ː": 48,
|
281 |
+
"˞": 76,
|
282 |
+
"ˠ": 270,
|
283 |
+
"ˡ": 297,
|
284 |
+
"ˣ": 122,
|
285 |
+
"ˤ": 276,
|
286 |
+
"̃": 149,
|
287 |
+
"̇": 178,
|
288 |
+
"̞": 94,
|
289 |
+
"̪": 142,
|
290 |
+
"͡": 308,
|
291 |
+
"ΐ": 261,
|
292 |
+
"β": 138,
|
293 |
+
"θ": 162,
|
294 |
+
"θʼ": 77,
|
295 |
+
"θ̠": 152,
|
296 |
+
"θ̼": 310,
|
297 |
+
"χ": 223,
|
298 |
+
"χʼ": 125,
|
299 |
+
"ϊ": 148,
|
300 |
+
"ϋ": 46,
|
301 |
+
"ஃ": 139,
|
302 |
+
"ᵐ": 298,
|
303 |
+
"ᵑ": 114,
|
304 |
+
"ᶑ": 110,
|
305 |
+
"ᶑ̊": 11,
|
306 |
+
"ᶬ": 44,
|
307 |
+
"ᶮ": 101,
|
308 |
+
"ᶯ": 68,
|
309 |
+
"ᶰ": 305,
|
310 |
+
"ᶿ": 69,
|
311 |
+
"ⁿ": 255,
|
312 |
+
"ⱱ": 257,
|
313 |
+
"ⱱ̟": 263,
|
314 |
+
"ꞎ": 24
|
315 |
+
}
|
wav2vec2-large-xlsr-japlmthufielta-ipa2000/vocab_ipa_full.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"t\u0361s": 0, "\u027a": 1, "\u0261\u0306": 2, "k\u01c1": 3, "\u027e\u033c": 4, "\u0273\u030a": 5, "\u014b\u01c0": 6, "t\u031a": 7, "z": 8, "\u029b\u0325": 9, "\u0262\u0306": 10, "\u1d91\u030a": 11, "\u0254": 12, "\u0279\u0320\u030a\u02d4": 13, "\u0255\u02bc": 14, "#": 15, "b": 16, "\u0255": 17, "t\u0361\u03b8": 18, "\u026a": 19, "\u0272": 20, "\u0261\u01c2": 21, "\u025c\u0303": 22, "\u0282": 23, "\ua78e": 24, "\u02a1": 25, "c\u0361\u00e7": 26, "\u026c\u02bc": 27, "\u029f\u031d": 28, "\u0270": 29, "\u00f0\u033c": 30, "\u0261\u01c1": 31, "\u028e": 32, "\u0276": 33, "s": 34, "\u0280": 35, "\u0274\u01c0": 36, "\u028c": 37, "\u025d": 38, "o\u0303": 39, "\u0153\u0303": 40, "\u01c0": 41, "\u00f0\u0320": 42, "\u014b\u01c3": 43, "\u1dac": 44, "l": 45, "\u03cb": 46, "t": 47, "\u02d0": 48, "\u0253\u0325": 49, "o\u031e": 50, "\u0279\u0320\u02d4": 51, "\u0295": 52, "e": 53, "k\u01c2": 54, "\u025c": 55, "\u014b": 56, "k\u0361p": 57, "\u025b\u0303": 58, "\u0271": 59, "b\u032a": 60, "\u0250\u0303": 61, "a\u0303": 62, "\u0290": 63, "\u0268\u0303": 64, "\u0260\u030a": 65, "n\u0325": 66, "\u0278\u02bc": 67, "\u1daf": 68, "\u1dbf": 69, "\u0252": 70, "\u0261": 71, "s\u02bc": 72, "p": 73, "\u02a1\u0306": 74, "\u025a": 75, "\u02de": 76, "\u03b8\u02bc": 77, "\u0284\u030a": 78, "\u00f8\u031e": 79, "\u02b7": 80, "\u0261\u0361b": 81, "q\u0298": 82, "k\u031a": 83, "y\u0303": 84, "'": 85, "p\u032a": 86, "k\u0361x": 87, "q\u02bc": 88, "t\u0361s\u02bc": 89, "\u0289\u0303": 90, "t\u0361\u0283": 91, "\u0261\u01c3": 92, "q\u0361\uab53": 93, "\u031e": 94, "\u0260": 95, "\u00e4": 96, "\u0153": 97, "\u0264\u0303": 98, "\u0258\u0303": 99, "f\u02bc": 100, "\u1dae": 101, "h": 102, "p\u0361f": 103, "w": 104, "d\u0361\u0291": 105, "\u0274\u01c3": 106, "\u00f8\u0303": 107, "\u0251\u0303": 108, "\u0275": 109, "\u1d91": 110, "\u0283\u02bc": 111, "\u0288\u02bc": 112, "\u00e1": 113, "\u1d51": 114, "\u0264": 115, "e\u0303": 116, "\u028e\u031d": 117, "n\u033c": 118, "\u0289": 119, "\u0264\u031e\u0303": 120, "\u029b": 121, "\u02e3": 122, "\u0261\u01c0": 123, "q": 124, "\u03c7\u02bc": 125, "d\u0361\u026e": 126, "\u0276\u0303": 127, "\u0273": 128, "\u028c\u0303": 129, "\u0272\u030a": 130, "k\u01c3": 131, "\u00f8\u031e\u0303": 132, "\u027e\u0325": 133, "k\u01c0": 134, "f": 135, "\u027b\u030a\u02d4": 136, "\u028e\u0306": 137, "\u03b2": 138, "\u0b83": 139, "\u00e6": 140, "k\u02bc": 141, "\u032a": 142, "\u025f\u0361\u029d": 143, "p\u02bc": 144, "\u029f\u031d\u030a": 145, "\u0292": 146, "\u00f0": 147, "\u03ca": 148, "\u0303": 149, "e\u031e": 150, "y": 151, "\u03b8\u0320": 152, "\u027a\u0325": 153, "\u02b2": 154, "\u029c": 155, "\u0259\u0303": 156, "\u00e4\u0303": 157, "\u029f": 158, "d\u033c": 159, "\u0258": 160, "d\u0361\u00f0": 161, "\u03b8": 162, "r": 163, "\u0259": 164, "t\u0361\u026c": 165, "\u00e7": 166, "\u0274": 167, "\u01c3": 168, "\u026e": 169, "\u027b": 170, "\u014b\u030a": 171, "\u0262\u0361\u0281": 172, "\u0294\u0361h": 173, "j": 174, "\u0264\u031e": 175, "\u028f\u0303": 176, "\u0262\u01c3": 177, "\u0307": 178, "\u0288\u0361\u0282\u02bc": 179, "q\u01c0": 180, "\u02b0": 181, "\u028a\u0303": 182, "p\u0361\u0278": 183, "\u025b": 184, "\u0283": 185, "\u027e": 186, "p\u032a\u0361f": 187, "q\u01c2": 188, "q\u0361\u03c7\u02bc": 189, "x": 190, "\u0256\u0361\u0290": 191, "g": 192, "n": 193, "\u025f": 194, "\u0262\u0298": 195, "\u0252\u0303": 196, "t\u033c": 197, "\u0262\u01c0": 198, "\u0127": 199, "u": 200, "\u0257\u0325": 201, "v": 202, "\u028e\u031d\u030a": 203, "\u0281": 204, "\u026c": 205, "\u027d\u030a": 206, " ": 207, "\u028b": 208, "c\u02bc": 209, "q\u01c3": 210, "\u026d\u0306": 211, "\u025e": 212, "t\u0361\u026c\u02bc": 213, "kx\u02bc": 214, "d": 215, "\u026a\u0303": 216, "d\u0361\u0292": 217, "\u0288": 218, "\u02a1\u0361\u029c": 219, "\u0251": 220, "\u025e\u0303": 221, "\u0279": 222, "\u03c7": 223, "o\u031e\u0303": 224, "\u00e9": 225, "\u0291": 226, "k\u0298": 227, "t\u02bc": 228, "m\u0325": 229, "\u026f\u0303": 230, "\u0275\u0303": 231, "\u026d\u02d4": 232, "\u0257": 233, "\u02a1\u02bc": 234, "\u0294": 235, "\u0274\u01c2": 236, "\u029f\u0306": 237, "\u0267": 238, "\u028a": 239, "\u028f": 240, "\u014b\u01c1": 241, "\u0280\u0325": 242, "a": 243, "k": 244, "\u026d": 245, "\u0262\u01c2": 246, "q\u0361\u02a1": 247, "\u0256": 248, "\u027d": 249, "m": 250, "\u014b\u0298": 251, "\u0261\u0361\u0263": 252, "\u0284": 253, "\u026d\u0325\u0306": 254, "\u207f": 255, "\u00e6\u0303": 256, "\u2c71": 257, "t\u0361\u0255": 258, "\u0262": 259, "\u0268": 260, "\u0390": 261, "\u0274\u0298": 262, "\u2c71\u031f": 263, "\u0265\u030a": 264, "\u0262\u01c1": 265, "\u0282\u02bc": 266, "\u0263": 267, "\u0265": 268, "\u0294\u031e": 269, "\u02e0": 270, "\u027b\u02d4": 271, "\u0274\u01c1": 272, "\u0288\u0361\u0282": 273, "\u02a2": 274, "\u0254\u0303": 275, "\u02e4": 276, "i": 277, "b\u0361\ua7b5": 278, "t\u0361\u0283\u02bc": 279, "\u026f": 280, "\u0261\u0298": 281, "e\u031e\u0303": 282, "\u00f8": 283, "x\u02bc": 284, "\u02bc": 285, "q\u01c1": 286, "r\u0325": 287, "\u028d": 288, "\u0278": 289, "\u014b\u01c2": 290, "t\u032a\u0361\u03b8\u02bc": 291, "c": 292, "p\u031a": 293, "o": 294, "\u0253": 295, "u\u0303": 296, "\u02e1": 297, "\u1d50": 298, "\u0299\u0325": 299, "\u0250": 300, "\u0299": 301, "\u029f\u0320": 302, "\u029d": 303, "b\u032a\u0361v": 304, "\u1db0": 305, "\u02a1\u0361\u02a2": 306, "d\u0361z": 307, "\u0361": 308, "\u014b\u0361m": 309, "\u03b8\u033c": 310, "[UNK]": 311, "[PAD]": 312}
|