first commit
Browse files- config.json +76 -0
- optimizer.pt +3 -0
- preprocessor_config.json +8 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +100 -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": 44,
|
74 |
+
"transformers_version": "4.4.0",
|
75 |
+
"vocab_size": 45
|
76 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35567b797d2ad024959817f25246b0d06ececc4dd794d69da7e9334950b455aa
|
3 |
+
size 2490446215
|
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:a20efe1c5480b033037f9ee3e21e24d9a51cf765fd5b96f0375b02012664b7b0
|
3 |
+
size 1262118359
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0818666afb82b7b432824bd91f7b1cbfd826c0bbd672aea23cda693e38746b70
|
3 |
+
size 623
|
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": "|"}
|
trainer_state.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 18.46153846153846,
|
5 |
+
"global_step": 1200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 3.08,
|
12 |
+
"learning_rate": 0.00011999999999999999,
|
13 |
+
"loss": 5.7855,
|
14 |
+
"step": 200
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 3.08,
|
18 |
+
"eval_loss": 3.094594717025757,
|
19 |
+
"eval_runtime": 32.9209,
|
20 |
+
"eval_samples_per_second": 7.017,
|
21 |
+
"eval_wer": 1.0,
|
22 |
+
"step": 200
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 6.15,
|
26 |
+
"learning_rate": 0.00023999999999999998,
|
27 |
+
"loss": 3.0293,
|
28 |
+
"step": 400
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 6.15,
|
32 |
+
"eval_loss": 3.005324125289917,
|
33 |
+
"eval_runtime": 32.0726,
|
34 |
+
"eval_samples_per_second": 7.202,
|
35 |
+
"eval_wer": 1.0,
|
36 |
+
"step": 400
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 9.23,
|
40 |
+
"learning_rate": 0.0002625,
|
41 |
+
"loss": 1.9629,
|
42 |
+
"step": 600
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 9.23,
|
46 |
+
"eval_loss": 1.0649160146713257,
|
47 |
+
"eval_runtime": 32.4082,
|
48 |
+
"eval_samples_per_second": 7.128,
|
49 |
+
"eval_wer": 0.7503426222019187,
|
50 |
+
"step": 600
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 12.31,
|
54 |
+
"learning_rate": 0.00018749999999999998,
|
55 |
+
"loss": 0.9013,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 12.31,
|
60 |
+
"eval_loss": 0.8863689303398132,
|
61 |
+
"eval_runtime": 32.197,
|
62 |
+
"eval_samples_per_second": 7.175,
|
63 |
+
"eval_wer": 0.6196893558702604,
|
64 |
+
"step": 800
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 15.38,
|
68 |
+
"learning_rate": 0.0001125,
|
69 |
+
"loss": 0.6283,
|
70 |
+
"step": 1000
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 15.38,
|
74 |
+
"eval_loss": 0.8295900821685791,
|
75 |
+
"eval_runtime": 32.1739,
|
76 |
+
"eval_samples_per_second": 7.18,
|
77 |
+
"eval_wer": 0.5616719963453631,
|
78 |
+
"step": 1000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 18.46,
|
82 |
+
"learning_rate": 3.75e-05,
|
83 |
+
"loss": 0.4995,
|
84 |
+
"step": 1200
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 18.46,
|
88 |
+
"eval_loss": 0.8448638319969177,
|
89 |
+
"eval_runtime": 32.5186,
|
90 |
+
"eval_samples_per_second": 7.104,
|
91 |
+
"eval_wer": 0.5415714938328003,
|
92 |
+
"step": 1200
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"max_steps": 1300,
|
96 |
+
"num_train_epochs": 20,
|
97 |
+
"total_flos": 7.999595747693107e+18,
|
98 |
+
"trial_name": null,
|
99 |
+
"trial_params": null
|
100 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12f8d81898a4d31d043925ba819cf0ce4cfa60b145af57af0c27995159ac9a6b
|
3 |
+
size 2287
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ذ": 0, "آ": 1, "ز": 2, "ى": 3, ")": 4, "خ": 5, "ط": 6, "ض": 7, "ج": 8, "م": 9, "ك": 10, "ء": 11, "ح": 12, "ؤ": 13, "ا": 14, "ع": 16, "ه": 17, "ق": 18, "ب": 19, "غ": 20, "ر": 21, "د": 22, "ن": 23, "#": 24, "(": 25, "ة": 26, "س": 27, "ظ": 28, "ي": 29, "ث": 30, "ئ": 31, "ش": 32, "ف": 33, "ت": 34, "ص": 35, "و": 36, "إ": 37, "،": 38, "ّ": 39, "أ": 40, "ل": 41, "؟": 42, "|": 15, "[UNK]": 43, "[PAD]": 44}
|