cahya commited on
Commit
bf864d5
1 Parent(s): 3c7054a

Model save

Browse files
config.json CHANGED
@@ -98,6 +98,7 @@
98
  1,
99
  1
100
  ],
 
101
  "transformers_version": "4.17.0.dev0",
102
  "use_weighted_layer_sum": false,
103
  "vocab_size": 40,
 
98
  1,
99
  1
100
  ],
101
+ "torch_dtype": "float32",
102
  "transformers_version": "4.17.0.dev0",
103
  "use_weighted_layer_sum": false,
104
  "vocab_size": 40,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:159724d9dcd401b0ccac2026c00a404a25f6cb464c80a816d6274676c20dac6c
3
  size 377694615
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d05055166909e6f0c2c92d51c1d2bcbca00165dbfcc573864d195cd6507063e
3
  size 377694615
run.sh CHANGED
@@ -5,7 +5,7 @@ python run_speech_recognition_ctc.py \
5
  --output_dir="./" \
6
  --overwrite_output_dir \
7
  --num_train_epochs="1" \
8
- --per_device_train_batch_size="16" \
9
  --per_device_eval_batch_size="2" \
10
  --gradient_accumulation_steps="4" \
11
  --learning_rate="3e-4" \
 
5
  --output_dir="./" \
6
  --overwrite_output_dir \
7
  --num_train_epochs="1" \
8
+ --per_device_train_batch_size="32" \
9
  --per_device_eval_batch_size="2" \
10
  --gradient_accumulation_steps="4" \
11
  --learning_rate="3e-4" \
tmp.0/config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cahya/wav2vec2-base-turkish-artificial",
3
+ "activation_dropout": 0.1,
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": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.0,
56
+ "hidden_size": 768,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "layer_norm_eps": 1e-05,
60
+ "layerdrop": 0.0,
61
+ "mask_feature_length": 64,
62
+ "mask_feature_min_masks": 0,
63
+ "mask_feature_prob": 0.25,
64
+ "mask_time_length": 10,
65
+ "mask_time_min_masks": 2,
66
+ "mask_time_prob": 0.75,
67
+ "model_type": "wav2vec2",
68
+ "num_adapter_layers": 3,
69
+ "num_attention_heads": 12,
70
+ "num_codevector_groups": 2,
71
+ "num_codevectors_per_group": 320,
72
+ "num_conv_pos_embedding_groups": 16,
73
+ "num_conv_pos_embeddings": 128,
74
+ "num_feat_extract_layers": 7,
75
+ "num_hidden_layers": 12,
76
+ "num_negatives": 100,
77
+ "output_hidden_size": 768,
78
+ "pad_token_id": 39,
79
+ "proj_codevector_dim": 256,
80
+ "tdnn_dilation": [
81
+ 1,
82
+ 2,
83
+ 3,
84
+ 1,
85
+ 1
86
+ ],
87
+ "tdnn_dim": [
88
+ 512,
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 1500
93
+ ],
94
+ "tdnn_kernel": [
95
+ 5,
96
+ 3,
97
+ 3,
98
+ 1,
99
+ 1
100
+ ],
101
+ "transformers_version": "4.17.0.dev0",
102
+ "use_weighted_layer_sum": false,
103
+ "vocab_size": 40,
104
+ "xvector_output_dim": 512
105
+ }
tmp.0/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": "Wav2Vec2ProcessorWithLM",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
tmp.0/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "pad_token": "[PAD]"}
tmp.0/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": null, "eos_token": null, "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
tmp.0/vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"-": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "â": 28, "ç": 29, "ë": 30, "î": 31, "ö": 32, "ü": 33, "ğ": 34, "ı": 35, "ş": 36, "̇": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebfc6f65c15f4f177ecb6ae8c248f7219ba01d4503236f9652468b35e689ef73
3
- size 2927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a10bcc5d960643107542b1720e90ec5f5d76d687e1e4640d575348a7a1a39a6
3
+ size 2991