Hugging Face's logo

ylacombe
/
wav2vec2-common_voice-ps-demo

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Pashto
wav2vec2-conformer
mozilla-foundation/common_voice_16_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ylacombe HF staff commited on
Commit
f16a020
•
1 Parent(s): a71981e

Training in progress, step 400

Browse files
Files changed (23) hide show
  1. added_tokens.json +4 -0
  2. config.json +117 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +10 -0
  5. runs/Jan01_19-59-19_vorace/events.out.tfevents.1704139215.vorace.77248.0 +3 -0
  6. runs/Jan01_20-06-34_vorace/events.out.tfevents.1704139641.vorace.77697.0 +3 -0
  7. runs/Jan01_20-09-52_vorace/events.out.tfevents.1704139840.vorace.79086.0 +3 -0
  8. runs/Jan01_20-12-00_vorace/events.out.tfevents.1704139968.vorace.81128.0 +3 -0
  9. runs/Jan01_20-18-39_vorace/events.out.tfevents.1704140376.vorace.86676.0 +3 -0
  10. runs/Jan01_21-26-29_vorace/events.out.tfevents.1704144435.vorace.114175.0 +3 -0
  11. runs/Jan01_21-36-34_vorace/events.out.tfevents.1704145041.vorace.116853.0 +3 -0
  12. runs/Jan01_21-40-28_vorace/events.out.tfevents.1704145283.vorace.117906.0 +3 -0
  13. runs/Jan01_21-46-52_vorace/events.out.tfevents.1704145666.vorace.119183.0 +3 -0
  14. runs/Jan01_21-49-00_vorace/events.out.tfevents.1704145793.vorace.119943.0 +3 -0
  15. runs/Jan01_21-51-16_vorace/events.out.tfevents.1704145982.vorace.120653.0 +3 -0
  16. runs/Jan01_21-55-00_vorace/events.out.tfevents.1704146146.vorace.122027.0 +3 -0
  17. runs/Jan01_21-56-35_vorace/events.out.tfevents.1704146272.vorace.122562.0 +3 -0
  18. runs/Jan01_21-59-31_vorace/events.out.tfevents.1704146438.vorace.123562.0 +3 -0
  19. runs/Jan01_22-09-15_vorace/events.out.tfevents.1704147001.vorace.125432.0 +3 -0
  20. special_tokens_map.json +30 -0
  21. tokenizer_config.json +47 -0
  22. training_args.bin +3 -0
  23. vocab.json +56 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 55,
3
+ "<s>": 54
4
+ }
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ylacombe/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ConformerForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 768,
14
+ "codevector_dim": 768,
15
+ "conformer_conv_dropout": 0.1,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "conv_dim": [
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 160
27
+ ],
28
+ "conv_kernel": [
29
+ 10,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 3,
34
+ 2,
35
+ 2
36
+ ],
37
+ "conv_stride": [
38
+ 5,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2
45
+ ],
46
+ "ctc_loss_reduction": "mean",
47
+ "ctc_zero_infinity": false,
48
+ "diversity_loss_weight": 0.1,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "swish",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "left_max_position_embeddings": 64,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "max_source_positions": 5000,
70
+ "model_type": "wav2vec2-conformer",
71
+ "non_causal_depth_wise_conv": false,
72
+ "num_adapter_layers": 0,
73
+ "num_attention_heads": 16,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 24,
80
+ "num_negatives": 100,
81
+ "output_hidden_size": 1024,
82
+ "pad_token_id": 53,
83
+ "position_embeddings_type": "relative_key",
84
+ "proj_codevector_dim": 768,
85
+ "right_max_position_embeddings": 8,
86
+ "rotary_embedding_base": 10000,
87
+ "skip_encoder_layer_norm": true,
88
+ "skip_feature_encoder": true,
89
+ "skip_pos_conv_embed": true,
90
+ "tdnn_dilation": [
91
+ 1,
92
+ 2,
93
+ 3,
94
+ 1,
95
+ 1
96
+ ],
97
+ "tdnn_dim": [
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 1500
103
+ ],
104
+ "tdnn_kernel": [
105
+ 5,
106
+ 3,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.37.0.dev0",
113
+ "use_adapter_with_attention": false,
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 56,
116
+ "xvector_output_dim": 512
117
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3a61f4060b5b624b216641234cfc8bf36c247899f525ce09a089f6fd601469
3
+ size 2322308176
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 1,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000,
9
+ "stride": 2
10
+ }
runs/Jan01_19-59-19_vorace/events.out.tfevents.1704139215.vorace.77248.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3540ad70b0598e26c58dfc2413e914ef56cec763e69fd0b513c2e913dd14807
3
+ size 6155
runs/Jan01_20-06-34_vorace/events.out.tfevents.1704139641.vorace.77697.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d787ebd181adcb55bc77f0b4cab6d9fe2107eadcab07444a52ba1b80f5329c
3
+ size 6155
runs/Jan01_20-09-52_vorace/events.out.tfevents.1704139840.vorace.79086.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5ac753550809061abb99a2f534180e5d624cf6402587a62ebb2f0c54961cd5
3
+ size 6155
runs/Jan01_20-12-00_vorace/events.out.tfevents.1704139968.vorace.81128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecad209979fb85601e2beede1e9126758cb9700806726693604ed67fbba740a
3
+ size 6155
runs/Jan01_20-18-39_vorace/events.out.tfevents.1704140376.vorace.86676.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2cc11868c5020c63e67df6f4434200c8df98a4654da36f93777f5691b24a3df
3
+ size 6155
runs/Jan01_21-26-29_vorace/events.out.tfevents.1704144435.vorace.114175.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b95ca43f0b30e162f3a1cab37f4283a412c42a0ee21f8d3dc5249ff4f7d8212
3
+ size 6155
runs/Jan01_21-36-34_vorace/events.out.tfevents.1704145041.vorace.116853.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6c4136871dd55f10b40512c07f2a6cbd442a4d7a8a1c016ae65c7fe847cda6
3
+ size 6155
runs/Jan01_21-40-28_vorace/events.out.tfevents.1704145283.vorace.117906.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d35e0931bd020526572d7a0da2f84f766974c0d55eb4cca9043e4bc7f3b124
3
+ size 6155
runs/Jan01_21-46-52_vorace/events.out.tfevents.1704145666.vorace.119183.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fffd72fa0029c2c3229159c7edb17bb09899ad31c291829153a09a9644a236
3
+ size 6155
runs/Jan01_21-49-00_vorace/events.out.tfevents.1704145793.vorace.119943.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f1dbe316f44619a073959a4efd8a92e38e9631fbb64400ca47e5a17b92372d9
3
+ size 6155
runs/Jan01_21-51-16_vorace/events.out.tfevents.1704145982.vorace.120653.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0c4f8a820269a9118f7970133d0c15ea31bb57ad1a76d415a44b6f6f80f04b
3
+ size 6155
runs/Jan01_21-55-00_vorace/events.out.tfevents.1704146146.vorace.122027.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9d55afd3631be146a8b3adb2c15f7809972b9eedcaf63e224bb858ee937a0c
3
+ size 6155
runs/Jan01_21-56-35_vorace/events.out.tfevents.1704146272.vorace.122562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ceb3045863b52c59085eb49bc03e76f7554a1720c1af72fac34b5e21fca7b46
3
+ size 6155
runs/Jan01_21-59-31_vorace/events.out.tfevents.1704146438.vorace.123562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3c6f2b47cb7a18f0ee91742d38bbde1f684a0c1240e3c6f9e4309ea4670355
3
+ size 6155
runs/Jan01_22-09-15_vorace/events.out.tfevents.1704147001.vorace.125432.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe98ac9d997c23a90dd4d2737aefa22cd07628ea543f98118af4fa0af5134116
3
+ size 7421
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "52": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "53": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "54": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "55": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43136803fc8c9b950772f3ba9057996d58d43a6113498c3471c7f0b0685f990d
3
+ size 4728
vocab.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 53,
3
+ "[UNK]": 52,
4
+ "|": 0,
5
+ "،": 1,
6
+ "؛": 2,
7
+ "؟": 3,
8
+ "آ": 4,
9
+ "ئ": 5,
10
+ "ا": 6,
11
+ "ب": 7,
12
+ "ت": 8,
13
+ "ث": 9,
14
+ "ج": 10,
15
+ "ح": 11,
16
+ "خ": 12,
17
+ "د": 13,
18
+ "ذ": 14,
19
+ "ر": 15,
20
+ "ز": 16,
21
+ "س": 17,
22
+ "ش": 18,
23
+ "ص": 19,
24
+ "ض": 20,
25
+ "ط": 21,
26
+ "ظ": 22,
27
+ "ع": 23,
28
+ "غ": 24,
29
+ "ف": 25,
30
+ "ق": 26,
31
+ "ل": 27,
32
+ "م": 28,
33
+ "ن": 29,
34
+ "ه": 30,
35
+ "و": 31,
36
+ "ى": 32,
37
+ "ي": 33,
38
+ "ټ": 34,
39
+ "پ": 35,
40
+ "ځ": 36,
41
+ "څ": 37,
42
+ "چ": 38,
43
+ "ډ": 39,
44
+ "ړ": 40,
45
+ "ږ": 41,
46
+ "ژ": 42,
47
+ "ښ": 43,
48
+ "ک": 44,
49
+ "ګ": 45,
50
+ "گ": 46,
51
+ "ڼ": 47,
52
+ "ۀ": 48,
53
+ "ی": 49,
54
+ "ۍ": 50,
55
+ "ې": 51
56
+ }