[email protected]
commited on
Commit
•
929b3dc
1
Parent(s):
3b1a83f
update
Browse files- added_tokens.json +1 -0
- config.json +76 -0
- preprocessor_config.json +8 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +32 -0
- training_args.bin +3 -0
- vocab.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 107, "</s>": 108}
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-29 12:40:04.541683/checkpoint-75",
|
3 |
+
"activation_dropout": 0.1,
|
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": true,
|
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": 106,
|
74 |
+
"transformers_version": "4.4.0",
|
75 |
+
"vocab_size": 107
|
76 |
+
}
|
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 |
+
}
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fade7a3b8bb9018ff522b8e7a49e1ee2b795bd4243903aeb0ca28991c0e9c3c
|
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": "|", "special_tokens_map_file": "/root/.cache/huggingface/transformers/8892bd2ba1de4982047602e38927ac6f215a3c401e48d5ed39a5341ed475633e.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-29 12:40:04.541683/checkpoint-75"}
|
trainer_state.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.06104659661650658,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-29 13:44:02.238365/checkpoint-25",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 50,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_loss": 0.06104659661650658,
|
13 |
+
"eval_runtime": 82.3366,
|
14 |
+
"eval_samples_per_second": 9.23,
|
15 |
+
"eval_wer": 0.16317016317016317,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.0,
|
20 |
+
"eval_loss": 0.06628068536520004,
|
21 |
+
"eval_runtime": 83.5033,
|
22 |
+
"eval_samples_per_second": 9.101,
|
23 |
+
"eval_wer": 0.16161616161616163,
|
24 |
+
"step": 50
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"max_steps": 250,
|
28 |
+
"num_train_epochs": 10,
|
29 |
+
"total_flos": 2.075614232631e+17,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": null
|
32 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f628a2baa271d692db28ee812eab102c39c44f9cf320b0ccd19f16f8ca01a4a3
|
3 |
+
size 2351
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"́": 0, "ò": 1, "ỳ": 2, "ủ": 3, "ằ": 4, "õ": 5, "ể": 6, "ỷ": 7, "ô": 8, "ẵ": 9, "ỹ": 10, "ễ": 11, "à": 12, "̣": 13, "ẫ": 14, "ẳ": 15, "h": 16, "ụ": 17, "đ": 18, "c": 19, "ồ": 20, "ộ": 21, "í": 22, "j": 23, "ă": 24, "ả": 25, "ì": 26, "ỗ": 27, "ǀ": 28, "o": 29, "̃": 30, "ặ": 31, "ẩ": 32, "ỉ": 33, "v": 34, "l": 35, "ĩ": 36, "ẻ": 37, "ừ": 38, "ầ": 39, "q": 40, "n": 41, "â": 42, "ử": 43, "m": 44, "ẽ": 45, "ọ": 46, "b": 47, "z": 48, "ế": 49, "“": 50, "ỵ": 51, "ệ": 52, "p": 53, "”": 54, "è": 55, "ã": 56, "ứ": 57, "d": 58, "x": 59, "ậ": 60, "w": 61, "ắ": 62, "t": 63, "ú": 64, "ỡ": 65, "ý": 66, "̉": 67, "ố": 68, "ợ": 69, "i": 70, "ạ": 71, "\\": 72, "é": 73, "ê": 74, "ẹ": 75, "ổ": 76, "ự": 77, "a": 78, "–": 79, "y": 80, "ờ": 81, "ở": 82, "s": 84, "ń": 85, "ớ": 86, "e": 87, "̀": 88, "ấ": 89, "ơ": 90, "ề": 91, "k": 92, "g": 93, "ó": 94, "ư": 95, "ù": 96, "ị": 97, "ũ": 98, "á": 99, "r": 100, "f": 101, "u": 102, "ữ": 103, "ỏ": 104, "|": 83, "[UNK]": 105, "[PAD]": 106}
|