LegolasTheElf commited on
Commit
bbcb605
1 Parent(s): 6d49fb2

Training in progress, step 400

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LegolasTheElf/Wav2Vec2_xls_r_300m_hi_final",
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": 0.1,
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_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.075,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 115,
81
+ "proj_codevector_dim": 768,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.17.0.dev0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 118,
107
+ "xvector_output_dim": 512
108
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48542a1a638dc5db69a288920fb62ad0bae1dff6ba7953a725c4be15fa9d4260
3
+ size 1262407473
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": " ", "processor_class": "Wav2Vec2Processor", "special_tokens_map_file": "/workspace/.cache/huggingface/transformers/df2d78003269fda0a80626d7299dd371cd535b2023ae7a60b0d00780a63ee4ef.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "LegolasTheElf/Wav2Vec2_xls_r_300m_hi_final", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885800269cf675c1c3053be46e91183a7f27a1b1fedb11f8f025169c0f9ec5c5
3
+ size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"र": 0, "'": 1, "i": 2, "W": 3, "’": 4, "w": 5, "आ": 6, "उ": 7, "h": 8, "ज़": 9, "झ": 10, "ऑ": 11, "N": 12, "r": 13, "ा": 14, "ी": 15, "ू": 16, "d": 17, "़": 18, "इ": 19, "y": 20, "व": 21, "u": 22, "ै": 23, "R": 24, "ई": 25, "फ": 26, "ब": 27, "घ": 28, "E": 29, "a": 30, "ऐ": 31, "ढ": 32, "ख": 33, "M": 34, "o": 35, "J": 36, "ॉ": 37, "V": 38, "Z": 39, "ः": 40, "c": 41, "ह": 42, "य": 43, "अ": 44, "n": 45, "ढ़": 46, "श": 47, "त": 48, "l": 49, "s": 50, "F": 51, "S": 52, "ि": 53, "ण": 54, "B": 55, "ल": 56, "ं": 57, "स": 58, "g": 59, "L": 60, "म": 61, "|": 62, "G": 63, "ँ": 64, "t": 65, "ष": 66, "च": 67, "x": 68, "प": 69, "ड़": 70, "ु": 71, "A": 72, "X": 73, "T": 74, "v": 75, "ठ": 76, "े": 77, "्": 78, " ": 79, "ड": 80, "p": 81, "ृ": 82, "j": 83, "ञ": 84, "द": 85, "m": 86, "ध": 87, "ॅ": 88, "ट": 89, "f": 90, "ओ": 91, "छ": 92, "b": 93, "क़": 94, "ऊ": 95, "ऋ": 96, "O": 97, "C": 98, "H": 99, "ज": 100, "ो": 101, "e": 102, "k": 103, "P": 104, "क": 105, "ग": 106, "भ": 107, "K": 108, "ए": 109, "ौ": 110, "औ": 111, "थ": 112, "न": 113, "[UNK]": 114, "[PAD]": 115, "<s>": 116, "</s>": 117}