patrickvonplaten
commited on
Commit
•
7cd7638
1
Parent(s):
f73b86e
Training in progress, step 400
Browse files- .gitignore +1 -0
- added_tokens.json +1 -0
- config.json +100 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Oct28_14-28-27_brutasse/1635431386.8407488/events.out.tfevents.1635431386.brutasse.20006.1 +3 -0
- runs/Oct28_14-28-27_brutasse/events.out.tfevents.1635431386.brutasse.20006.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +1 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 29, "</s>": 30}
|
config.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "asapp/sew-d-small-100k",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"SEWDForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"conv_bias": false,
|
12 |
+
"conv_dim": [
|
13 |
+
64,
|
14 |
+
128,
|
15 |
+
128,
|
16 |
+
128,
|
17 |
+
128,
|
18 |
+
256,
|
19 |
+
256,
|
20 |
+
256,
|
21 |
+
256,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512
|
26 |
+
],
|
27 |
+
"conv_kernel": [
|
28 |
+
10,
|
29 |
+
3,
|
30 |
+
1,
|
31 |
+
3,
|
32 |
+
1,
|
33 |
+
3,
|
34 |
+
1,
|
35 |
+
3,
|
36 |
+
1,
|
37 |
+
2,
|
38 |
+
1,
|
39 |
+
2,
|
40 |
+
1
|
41 |
+
],
|
42 |
+
"conv_stride": [
|
43 |
+
5,
|
44 |
+
2,
|
45 |
+
1,
|
46 |
+
2,
|
47 |
+
1,
|
48 |
+
2,
|
49 |
+
1,
|
50 |
+
2,
|
51 |
+
1,
|
52 |
+
2,
|
53 |
+
1,
|
54 |
+
2,
|
55 |
+
1
|
56 |
+
],
|
57 |
+
"ctc_loss_reduction": "mean",
|
58 |
+
"ctc_zero_infinity": false,
|
59 |
+
"eos_token_id": 2,
|
60 |
+
"feat_extract_activation": "gelu",
|
61 |
+
"feat_extract_norm": "group",
|
62 |
+
"feat_proj_dropout": 0.0,
|
63 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
64 |
+
"feature_layer_norm_eps": 1e-05,
|
65 |
+
"final_dropout": 0.0,
|
66 |
+
"hidden_act": "gelu_python",
|
67 |
+
"hidden_dropout": 0.0,
|
68 |
+
"hidden_size": 512,
|
69 |
+
"initializer_range": 0.02,
|
70 |
+
"intermediate_size": 2048,
|
71 |
+
"layer_norm_eps": 1e-07,
|
72 |
+
"layerdrop": 0.0,
|
73 |
+
"mask_feature_length": 10,
|
74 |
+
"mask_feature_prob": 0.0,
|
75 |
+
"mask_time_length": 10,
|
76 |
+
"mask_time_prob": 0.05,
|
77 |
+
"max_position_embeddings": 512,
|
78 |
+
"model_type": "sew-d",
|
79 |
+
"norm_rel_ebd": "layer_norm",
|
80 |
+
"num_attention_heads": 8,
|
81 |
+
"num_conv_pos_embedding_groups": 16,
|
82 |
+
"num_conv_pos_embeddings": 31,
|
83 |
+
"num_feat_extract_layers": 13,
|
84 |
+
"num_hidden_layers": 12,
|
85 |
+
"pad_token_id": 28,
|
86 |
+
"pos_att_type": [
|
87 |
+
"p2c",
|
88 |
+
"c2p"
|
89 |
+
],
|
90 |
+
"position_biased_input": false,
|
91 |
+
"position_buckets": 256,
|
92 |
+
"relative_attention": true,
|
93 |
+
"share_att_key": true,
|
94 |
+
"squeeze_factor": 2,
|
95 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
96 |
+
"torch_dtype": "float32",
|
97 |
+
"transformers_version": "4.12.0.dev0",
|
98 |
+
"use_weighted_layer_sum": false,
|
99 |
+
"vocab_size": 31
|
100 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:740813ac19550590c82764251f60832f23165929983da9262f70ed003c8e3226
|
3 |
+
size 164046635
|
runs/Oct28_14-28-27_brutasse/1635431386.8407488/events.out.tfevents.1635431386.brutasse.20006.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd58f54dae83dd6b9a779135762687febcd91b31e285ca16310b1c09699d7686
|
3 |
+
size 4571
|
runs/Oct28_14-28-27_brutasse/events.out.tfevents.1635431386.brutasse.20006.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e566004f99fa738f9f5b12316a619c052ede8946aaebb8bd9d31782929ade0ce
|
3 |
+
size 11910
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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": null, "tokenizer_file": null, "name_or_path": "./sew-d-small-100k-ft-timit-2", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9df908e94bec68bbb4c6bcaa4a54dd036bbc7821a4dc2bf5a9d91ba6dd6fb30
|
3 |
+
size 2863
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "|": 0, "[UNK]": 27, "[PAD]": 28}
|