Hugging Face's logo

nayerim
/
speecht5-indonesian-tts

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
 Metrics Community
1
nayerim commited on
Commit
2daef3c
·
verified ·
1 Parent(s): 3bf957d

Training in progress, step 500

Browse files
Files changed (17) hide show
  1. added_tokens.json +4 -0
  2. config.json +91 -0
  3. model.safetensors +3 -0
  4. runs/Aug22_08-00-30_2e5063f19d8d/events.out.tfevents.1755849637.2e5063f19d8d.175.0 +3 -0
  5. runs/Aug22_08-12-43_2e5063f19d8d/events.out.tfevents.1755850383.2e5063f19d8d.175.1 +3 -0
  6. runs/Aug22_08-23-14_2e5063f19d8d/events.out.tfevents.1755851000.2e5063f19d8d.175.2 +3 -0
  7. runs/Aug22_08-25-39_2e5063f19d8d/events.out.tfevents.1755851146.2e5063f19d8d.175.3 +3 -0
  8. runs/Aug22_08-32-32_2e5063f19d8d/events.out.tfevents.1755851560.2e5063f19d8d.175.4 +3 -0
  9. runs/Aug22_09-20-47_2e5063f19d8d/events.out.tfevents.1755854449.2e5063f19d8d.13368.0 +3 -0
  10. runs/Aug22_09-33-42_2e5063f19d8d/events.out.tfevents.1755855223.2e5063f19d8d.13368.1 +3 -0
  11. runs/Aug22_09-36-06_2e5063f19d8d/events.out.tfevents.1755855367.2e5063f19d8d.13368.2 +3 -0
  12. runs/Aug22_09-37-57_2e5063f19d8d/events.out.tfevents.1755855478.2e5063f19d8d.13368.3 +3 -0
  13. runs/Aug22_09-39-43_2e5063f19d8d/events.out.tfevents.1755855584.2e5063f19d8d.13368.4 +3 -0
  14. special_tokens_map.json +13 -0
  15. spm_char.model +3 -0
  16. tokenizer_config.json +64 -0
  17. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79
4
+ }
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "SpeechT5ForTextToSpeech"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "conv_bias": false,
10
+ "conv_dim": [
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512
18
+ ],
19
+ "conv_kernel": [
20
+ 10,
21
+ 3,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 2,
26
+ 2
27
+ ],
28
+ "conv_stride": [
29
+ 5,
30
+ 2,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2
36
+ ],
37
+ "decoder_attention_heads": 12,
38
+ "decoder_ffn_dim": 3072,
39
+ "decoder_layerdrop": 0.1,
40
+ "decoder_layers": 6,
41
+ "decoder_start_token_id": 2,
42
+ "encoder_attention_heads": 12,
43
+ "encoder_ffn_dim": 3072,
44
+ "encoder_layerdrop": 0.1,
45
+ "encoder_layers": 12,
46
+ "encoder_max_relative_position": 160,
47
+ "eos_token_id": 2,
48
+ "feat_extract_activation": "gelu",
49
+ "feat_extract_norm": "group",
50
+ "feat_proj_dropout": 0.0,
51
+ "guided_attention_loss_num_heads": 2,
52
+ "guided_attention_loss_scale": 10.0,
53
+ "guided_attention_loss_sigma": 0.4,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.1,
56
+ "hidden_size": 768,
57
+ "initializer_range": 0.02,
58
+ "is_encoder_decoder": true,
59
+ "layer_norm_eps": 1e-05,
60
+ "mask_feature_length": 10,
61
+ "mask_feature_min_masks": 0,
62
+ "mask_feature_prob": 0.0,
63
+ "mask_time_length": 10,
64
+ "mask_time_min_masks": 2,
65
+ "mask_time_prob": 0.05,
66
+ "max_length": null,
67
+ "max_speech_positions": 1876,
68
+ "max_text_positions": 600,
69
+ "model_type": "speecht5",
70
+ "num_conv_pos_embedding_groups": 16,
71
+ "num_conv_pos_embeddings": 128,
72
+ "num_feat_extract_layers": 7,
73
+ "num_mel_bins": 80,
74
+ "pad_token_id": 1,
75
+ "positional_dropout": 0.1,
76
+ "reduction_factor": 2,
77
+ "scale_embedding": false,
78
+ "speaker_embedding_dim": 512,
79
+ "speech_decoder_postnet_dropout": 0.5,
80
+ "speech_decoder_postnet_kernel": 5,
81
+ "speech_decoder_postnet_layers": 5,
82
+ "speech_decoder_postnet_units": 256,
83
+ "speech_decoder_prenet_dropout": 0.5,
84
+ "speech_decoder_prenet_layers": 2,
85
+ "speech_decoder_prenet_units": 256,
86
+ "torch_dtype": "float32",
87
+ "transformers_version": "4.55.2",
88
+ "use_cache": false,
89
+ "use_guided_attention_loss": true,
90
+ "vocab_size": 81
91
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bff6b7e6e651e8c2a85b008fecfacd71a6aea434a7d7aa564ab004d82a18cd9
3
+ size 577789320
runs/Aug22_08-00-30_2e5063f19d8d/events.out.tfevents.1755849637.2e5063f19d8d.175.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935bcd4836f1bd03d029efbb32c38995dcd945227d4e74d2b0ee24dc2bc92cd7
3
+ size 6612
runs/Aug22_08-12-43_2e5063f19d8d/events.out.tfevents.1755850383.2e5063f19d8d.175.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac491dbb52f5872c3669899755f479a555be4e5201e41707c8cea856685e3d1
3
+ size 6612
runs/Aug22_08-23-14_2e5063f19d8d/events.out.tfevents.1755851000.2e5063f19d8d.175.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89aa28032980b97fa502d84123144adf72556c9aed3e014ba62fa12b3515867
3
+ size 6612
runs/Aug22_08-25-39_2e5063f19d8d/events.out.tfevents.1755851146.2e5063f19d8d.175.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743281c432a1f7d0de88df0abee5484fd64a1ade4875c18df1eda575d096b808
3
+ size 6612
runs/Aug22_08-32-32_2e5063f19d8d/events.out.tfevents.1755851560.2e5063f19d8d.175.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe5a0245b10f0c7f9ba9adb62453943306bc9c1c56f18a15976b95aa3035b56
3
+ size 6612
runs/Aug22_09-20-47_2e5063f19d8d/events.out.tfevents.1755854449.2e5063f19d8d.13368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce89ee9facac40f501259d240e64b9409a11069cb4aa064527214151b5c3ffc2
3
+ size 6612
runs/Aug22_09-33-42_2e5063f19d8d/events.out.tfevents.1755855223.2e5063f19d8d.13368.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51375ff9726338f7c4cdfb437b0d26bc2398ef097ba393aeaf0785acd7357feb
3
+ size 6612
runs/Aug22_09-36-06_2e5063f19d8d/events.out.tfevents.1755855367.2e5063f19d8d.13368.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80966189d0bf77048744a44b200a3c533bd5d69793a2a4fd1e779a03c9327c4c
3
+ size 6612
runs/Aug22_09-37-57_2e5063f19d8d/events.out.tfevents.1755855478.2e5063f19d8d.13368.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba38deaa4ee7ae420a89c4e8756718d36d0e2d2d15292fdc6015bcdbd5aced33
3
+ size 6612
runs/Aug22_09-39-43_2e5063f19d8d/events.out.tfevents.1755855584.2e5063f19d8d.13368.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9262bcbea29d634e0213bb841e9b460d43362894b53476451d117a532a8edede
3
+ size 11084
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": {
5
+ "content": "<mask>",
6
+ "lstrip": true,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "pad_token": "<pad>",
12
+ "unk_token": "<unk>"
13
+ }
spm_char.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
3
+ size 238473
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "79": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "80": {
44
+ "content": "<ctc_blank>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "eos_token": "</s>",
55
+ "extra_special_tokens": {},
56
+ "mask_token": "<mask>",
57
+ "model_max_length": 600,
58
+ "normalize": false,
59
+ "pad_token": "<pad>",
60
+ "processor_class": "SpeechT5Processor",
61
+ "sp_model_kwargs": {},
62
+ "tokenizer_class": "SpeechT5Tokenizer",
63
+ "unk_token": "<unk>"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b5dc3676eb4dfd21201b263811c33d00604832c2a774a4621ed66f2f1e5dee
3
+ size 5969