patrickvonplaten
commited on
Commit
•
1a98507
1
Parent(s):
ad74a4a
Training in progress, step 400
Browse files- .gitignore +1 -0
- added_tokens.json +1 -0
- config.json +84 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Oct22_17-23-07_brutasse/1634923601.2630305/events.out.tfevents.1634923601.brutasse.19691.1 +3 -0
- runs/Oct22_17-23-07_brutasse/events.out.tfevents.1634923601.brutasse.19691.0 +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 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/unispeech-large-1500h-cv",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"UniSpeechForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
+
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
+
"conv_dim": [
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512,
|
21 |
+
512
|
22 |
+
],
|
23 |
+
"conv_kernel": [
|
24 |
+
10,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
3,
|
29 |
+
2,
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"conv_stride": [
|
33 |
+
5,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2
|
40 |
+
],
|
41 |
+
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": false,
|
43 |
+
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
+
"eos_token_id": 2,
|
46 |
+
"feat_extract_activation": "gelu",
|
47 |
+
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
+
"feat_proj_dropout": 0.0,
|
50 |
+
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.0,
|
54 |
+
"hidden_size": 1024,
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 4096,
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"layerdrop": 0.0,
|
59 |
+
"mask_channel_length": 10,
|
60 |
+
"mask_channel_prob": 0.0,
|
61 |
+
"mask_feature_length": 10,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_space": 1,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"model_type": "unispeech",
|
67 |
+
"num_attention_heads": 16,
|
68 |
+
"num_codevector_groups": 2,
|
69 |
+
"num_codevectors_per_group": 320,
|
70 |
+
"num_conv_pos_embedding_groups": 16,
|
71 |
+
"num_conv_pos_embeddings": 128,
|
72 |
+
"num_ctc_classes": 80,
|
73 |
+
"num_feat_extract_layers": 7,
|
74 |
+
"num_hidden_layers": 24,
|
75 |
+
"num_negatives": 100,
|
76 |
+
"pad_token_id": 28,
|
77 |
+
"proj_codevector_dim": 768,
|
78 |
+
"replace_prob": 0.5,
|
79 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
80 |
+
"torch_dtype": "float32",
|
81 |
+
"transformers_version": "4.12.0.dev0",
|
82 |
+
"use_weighted_layer_sum": false,
|
83 |
+
"vocab_size": 31
|
84 |
+
}
|
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:a10893bb8b959dd4893e149dab8401d20632c686260ecd3355a2220a9a6e15a3
|
3 |
+
size 1262061783
|
runs/Oct22_17-23-07_brutasse/1634923601.2630305/events.out.tfevents.1634923601.brutasse.19691.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86072a159385aa14f5610e96a67445edd5ad94681956afeb9861070ec0904f51
|
3 |
+
size 4580
|
runs/Oct22_17-23-07_brutasse/events.out.tfevents.1634923601.brutasse.19691.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6acbbc2dee1fcba6d6023ba0c48c049d0eb31c320d78e8035e22a9327ad08ab
|
3 |
+
size 11911
|
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": "./unispeech-large-1500h-cv-timit", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:329acc65fd67b5aa55c5c9302409ec8b5307efcafafbacfb18f62e9dfdd561cd
|
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}
|