Commit
•
1bde6c3
1
Parent(s):
f778647
First version of the wav2vec2-large-xlsr-kn model and tokenizer.
Browse files- config.json +76 -0
- preprocessor_config.json +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +1 -0
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
3 |
+
"activation_dropout": 0.0,
|
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,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512
|
19 |
+
],
|
20 |
+
"conv_kernel": [
|
21 |
+
10,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
2,
|
27 |
+
2
|
28 |
+
],
|
29 |
+
"conv_stride": [
|
30 |
+
5,
|
31 |
+
2,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2
|
37 |
+
],
|
38 |
+
"ctc_loss_reduction": "mean",
|
39 |
+
"ctc_zero_infinity": false,
|
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",
|
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": 0.1,
|
55 |
+
"mask_channel_length": 10,
|
56 |
+
"mask_channel_min_space": 1,
|
57 |
+
"mask_channel_other": 0.0,
|
58 |
+
"mask_channel_prob": 0.0,
|
59 |
+
"mask_channel_selection": "static",
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_prob": 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,
|
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 |
+
"pad_token_id": 100,
|
74 |
+
"transformers_version": "4.5.0.dev0",
|
75 |
+
"vocab_size": 101
|
76 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": true,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56255e6468e3ae12ca97a0573c5170a70b9e73cc96699ba5e9da4cd480b59557
|
3 |
+
size 1262347927
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
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": "|"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afc7187af982f2cc7b7f9be7bdf85ffd484276fc48bdea7c481020731cd7a468
|
3 |
+
size 2287
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"6": 0, "೨": 1, "ೇ": 2, "ಛ": 3, "ಿ": 4, "ಞ": 5, "ಊ": 6, "೧": 7, "ಾ": 8, "n": 9, "'": 10, "ಆ": 11, "೯": 12, "/": 13, "2": 14, "ಉ": 15, "ಂ": 16, "8": 17, "ಢ": 18, "೪": 19, "೮": 20, "ಲ": 21, "ೌ": 22, "ಙ": 23, "ವ": 24, "ಬ": 25, "ಧ": 26, "ಗ": 27, "ೋ": 28, "ಳ": 29, "e": 30, "u": 31, "ಥ": 32, "ಭ": 33, "ಚ": 34, "೩": 35, "ಖ": 36, "’": 37, "ಓ": 38, "ಠ": 39, "ಈ": 40, "ಕ": 41, "ಔ": 42, "ು": 43, "ಋ": 45, "ತ": 46, "ಐ": 47, "ೀ": 48, "ೆ": 49, "ಮ": 50, "ಘ": 51, "೫": 52, "ೃ": 53, "": 54, "ೈ": 55, "೬": 56, "5": 57, "ಷ": 58, "t": 59, "1": 60, "": 61, "_": 62, "ಏ": 63, "r": 64, "ದ": 65, "ರ": 66, "x": 67, "ಇ": 68, "್": 69, "7": 70, "೭": 71, "(": 72, "ಫ": 73, "ನ": 74, "ೊ": 75, "ೂ": 76, "ಅ": 77, "ಪ": 78, "ಝ": 79, ")": 80, "ಜ": 81, "ಒ": 82, "ಯ": 83, "೦": 84, "3": 85, "4": 86, "l": 87, "ಶ": 88, "ಣ": 89, "ಟ": 90, "ಎ": 91, "ಸ": 92, "ಹ": 93, "ಃ": 94, "0": 95, "i": 96, "9": 97, "ಡ": 98, "|": 44, "[UNK]": 99, "[PAD]": 100}
|