Training in progress, epoch 1
Browse files- added_tokens.json +4 -0
- config.json +5 -8
- model.safetensors +1 -1
- preprocessor_config.json +1 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +48 -0
- training_args.bin +1 -1
- vocab.json +32 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 31,
|
3 |
+
"<s>": 30
|
4 |
+
}
|
config.json
CHANGED
@@ -10,7 +10,7 @@
|
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
"attention_dropout": 0.1,
|
13 |
-
"bos_token_id":
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 256,
|
16 |
"contrastive_logits_temperature": 0.1,
|
@@ -42,21 +42,18 @@
|
|
42 |
2,
|
43 |
2
|
44 |
],
|
45 |
-
"ctc_loss_reduction": "
|
46 |
"ctc_zero_infinity": false,
|
47 |
"diversity_loss_weight": 0.1,
|
48 |
"do_stable_layer_norm": false,
|
49 |
-
"eos_token_id":
|
50 |
"feat_extract_activation": "gelu",
|
51 |
-
"feat_extract_dropout": 0.0,
|
52 |
"feat_extract_norm": "group",
|
53 |
-
"feat_proj_dropout": 0.
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.1,
|
56 |
-
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
"hidden_dropout": 0.1,
|
59 |
-
"hidden_dropout_prob": 0.1,
|
60 |
"hidden_size": 768,
|
61 |
"initializer_range": 0.02,
|
62 |
"intermediate_size": 3072,
|
@@ -79,7 +76,7 @@
|
|
79 |
"num_hidden_layers": 12,
|
80 |
"num_negatives": 100,
|
81 |
"output_hidden_size": 768,
|
82 |
-
"pad_token_id":
|
83 |
"proj_codevector_dim": 256,
|
84 |
"tdnn_dilation": [
|
85 |
1,
|
|
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
"attention_dropout": 0.1,
|
13 |
+
"bos_token_id": 30,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 256,
|
16 |
"contrastive_logits_temperature": 0.1,
|
|
|
42 |
2,
|
43 |
2
|
44 |
],
|
45 |
+
"ctc_loss_reduction": "mean",
|
46 |
"ctc_zero_infinity": false,
|
47 |
"diversity_loss_weight": 0.1,
|
48 |
"do_stable_layer_norm": false,
|
49 |
+
"eos_token_id": 31,
|
50 |
"feat_extract_activation": "gelu",
|
|
|
51 |
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.0,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
"final_dropout": 0.1,
|
|
|
55 |
"hidden_act": "gelu",
|
56 |
"hidden_dropout": 0.1,
|
|
|
57 |
"hidden_size": 768,
|
58 |
"initializer_range": 0.02,
|
59 |
"intermediate_size": 3072,
|
|
|
76 |
"num_hidden_layers": 12,
|
77 |
"num_negatives": 100,
|
78 |
"output_hidden_size": 768,
|
79 |
+
"pad_token_id": 29,
|
80 |
"proj_codevector_dim": 256,
|
81 |
"tdnn_dilation": [
|
82 |
1,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377611120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1027b9f549fb4f5074a7a2ed2446d40d7bdeeac2465be0d7818eb759fa8c5f90
|
3 |
size 377611120
|
preprocessor_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": false,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
"return_attention_mask": false,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
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 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"28": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"29": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"30": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"31": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04870151b0266f9e4fe50fd0f5ca56fe5d3003aa0ee9fe2f62cfdc8f32fb5c33
|
3 |
size 5112
|
vocab.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 17,
|
3 |
+
"[PAD]": 29,
|
4 |
+
"[UNK]": 28,
|
5 |
+
"a": 14,
|
6 |
+
"b": 2,
|
7 |
+
"c": 6,
|
8 |
+
"d": 5,
|
9 |
+
"e": 11,
|
10 |
+
"f": 21,
|
11 |
+
"g": 9,
|
12 |
+
"h": 23,
|
13 |
+
"i": 8,
|
14 |
+
"j": 0,
|
15 |
+
"k": 20,
|
16 |
+
"l": 19,
|
17 |
+
"m": 13,
|
18 |
+
"n": 15,
|
19 |
+
"o": 25,
|
20 |
+
"p": 26,
|
21 |
+
"q": 22,
|
22 |
+
"r": 3,
|
23 |
+
"s": 16,
|
24 |
+
"t": 27,
|
25 |
+
"u": 18,
|
26 |
+
"v": 7,
|
27 |
+
"w": 12,
|
28 |
+
"x": 24,
|
29 |
+
"y": 10,
|
30 |
+
"z": 4,
|
31 |
+
"|": 1
|
32 |
+
}
|