initial push 1st try
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 +44 -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": 70,
|
74 |
+
"transformers_version": "4.4.0",
|
75 |
+
"vocab_size": 71
|
76 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e36aaf1858a24d803db0a490c64e5dd62fbdad7832df57072c1b306cab70de
|
3 |
+
size 2490659335
|
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 sha256:6100534b99cfe1d84ca744d05d3f994e2906bad2ef513efedd3eec3e36661154
|
3 |
+
size 1262224919
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b50cc95e12bd09b0797fb537b7270584feb80c90ed9167113cb636c72c3194d
|
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 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.297029702970297,
|
5 |
+
"global_step": 800,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.65,
|
12 |
+
"learning_rate": 0.00023999999999999998,
|
13 |
+
"loss": 6.8625,
|
14 |
+
"step": 400
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.65,
|
18 |
+
"eval_loss": 3.4594738483428955,
|
19 |
+
"eval_runtime": 211.356,
|
20 |
+
"eval_samples_per_second": 10.352,
|
21 |
+
"eval_wer": 1.0,
|
22 |
+
"step": 400
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 5.3,
|
26 |
+
"learning_rate": 7.832512315270935e-05,
|
27 |
+
"loss": 1.5787,
|
28 |
+
"step": 800
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 5.3,
|
32 |
+
"eval_loss": 0.6689605116844177,
|
33 |
+
"eval_runtime": 220.0088,
|
34 |
+
"eval_samples_per_second": 9.945,
|
35 |
+
"eval_wer": 0.6838202674440712,
|
36 |
+
"step": 800
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"max_steps": 906,
|
40 |
+
"num_train_epochs": 6,
|
41 |
+
"total_flos": 3.298739982613021e+18,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:856f3181b05eb1e8d3fc464f45704f4c8f04c07811d54bd5f1d8ef94d984ec90
|
3 |
+
size 2351
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ฑ": 0, "ฆ": 1, "ช": 2, "ฏ": 3, "า": 4, "ข": 5, "ฤ": 6, "ซ": 8, "เ": 9, "ี": 10, "ค": 11, "ฐ": 12, "๊": 13, "ุ": 14, "’": 15, "ิ": 16, "ั": 17, "ษ": 18, "ม": 19, "ส": 20, "ฟ": 21, "ก": 22, "ท": 23, "ว": 24, "ถ": 25, "ล": 26, "ต": 27, "ะ": 28, "ป": 29, "ย": 30, "ฒ": 31, "ญ": 32, "ฬ": 33, "ณ": 34, "ึ": 35, "'": 36, "็": 37, "พ": 38, "้": 39, "อ": 40, "ๆ": 41, "ศ": 42, "ำ": 43, "๋": 44, "ด": 45, "ธ": 46, "ผ": 47, "บ": 48, "ํ": 49, "ฎ": 50, "ู": 51, "ง": 52, "์": 53, "ใ": 54, "ๅ": 55, "ร": 56, "ไ": 57, "ฝ": 58, "จ": 59, "่": 60, "ภ": 61, "น": 62, "ื": 63, "โ": 64, "แ": 65, "ฮ": 66, "ห": 67, "ฉ": 68, "|": 7, "[UNK]": 69, "[PAD]": 70}
|