Hugging Face's logo

mihael974
/
speecht5_tts_voxpopuli_hr

Text-to-Audio
Transformers
TensorBoard
Safetensors
Croatian
speecht5
v1.0
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mihael974 commited on
Commit
bdc158d
•
1 Parent(s): 184983b

Training in progress, step 1000

Browse files
Files changed (25) hide show
  1. added_tokens.json +4 -0
  2. config.json +92 -0
  3. model.safetensors +3 -0
  4. runs/Jan09_16-22-57_5e7c64e924b5/events.out.tfevents.1704817385.5e7c64e924b5.7903.0 +3 -0
  5. runs/Jan09_16-31-20_5e7c64e924b5/events.out.tfevents.1704817885.5e7c64e924b5.7903.1 +3 -0
  6. runs/Jan09_16-31-58_5e7c64e924b5/events.out.tfevents.1704817922.5e7c64e924b5.7903.2 +3 -0
  7. runs/Jan09_16-32-14_5e7c64e924b5/events.out.tfevents.1704817937.5e7c64e924b5.7903.3 +3 -0
  8. runs/Jan09_16-32-44_5e7c64e924b5/events.out.tfevents.1704817968.5e7c64e924b5.7903.4 +3 -0
  9. runs/Jan09_16-33-17_5e7c64e924b5/events.out.tfevents.1704818000.5e7c64e924b5.7903.5 +3 -0
  10. runs/Jan09_16-34-22_5e7c64e924b5/events.out.tfevents.1704818065.5e7c64e924b5.7903.6 +3 -0
  11. runs/Jan09_16-38-35_5e7c64e924b5/events.out.tfevents.1704818318.5e7c64e924b5.7903.7 +3 -0
  12. runs/Jan09_16-39-18_5e7c64e924b5/events.out.tfevents.1704818361.5e7c64e924b5.7903.8 +3 -0
  13. runs/Jan09_16-39-36_5e7c64e924b5/events.out.tfevents.1704818379.5e7c64e924b5.7903.9 +3 -0
  14. runs/Jan09_16-43-26_5e7c64e924b5/events.out.tfevents.1704818610.5e7c64e924b5.7903.10 +3 -0
  15. runs/Jan09_16-53-59_5e7c64e924b5/events.out.tfevents.1704819243.5e7c64e924b5.7903.11 +3 -0
  16. runs/Jan09_16-54-39_5e7c64e924b5/events.out.tfevents.1704819282.5e7c64e924b5.7903.12 +3 -0
  17. runs/Jan09_16-55-07_5e7c64e924b5/events.out.tfevents.1704819311.5e7c64e924b5.7903.13 +3 -0
  18. runs/Jan09_16-55-21_5e7c64e924b5/events.out.tfevents.1704819324.5e7c64e924b5.7903.14 +3 -0
  19. runs/Jan09_16-55-41_5e7c64e924b5/events.out.tfevents.1704819344.5e7c64e924b5.7903.15 +3 -0
  20. runs/Jan09_17-00-57_5e7c64e924b5/events.out.tfevents.1704819669.5e7c64e924b5.7903.16 +3 -0
  21. runs/Jan09_17-11-44_5e7c64e924b5/events.out.tfevents.1704820308.5e7c64e924b5.7903.17 +3 -0
  22. special_tokens_map.json +13 -0
  23. spm_char.model +3 -0
  24. tokenizer_config.json +63 -0
  25. 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 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/speecht5_tts",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SpeechT5ForTextToSpeech"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "conv_bias": false,
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
+ "decoder_attention_heads": 12,
39
+ "decoder_ffn_dim": 3072,
40
+ "decoder_layerdrop": 0.1,
41
+ "decoder_layers": 6,
42
+ "decoder_start_token_id": 2,
43
+ "encoder_attention_heads": 12,
44
+ "encoder_ffn_dim": 3072,
45
+ "encoder_layerdrop": 0.1,
46
+ "encoder_layers": 12,
47
+ "encoder_max_relative_position": 160,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "guided_attention_loss_num_heads": 2,
53
+ "guided_attention_loss_scale": 10.0,
54
+ "guided_attention_loss_sigma": 0.4,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "is_encoder_decoder": true,
60
+ "layer_norm_eps": 1e-05,
61
+ "mask_feature_length": 10,
62
+ "mask_feature_min_masks": 0,
63
+ "mask_feature_prob": 0.0,
64
+ "mask_time_length": 10,
65
+ "mask_time_min_masks": 2,
66
+ "mask_time_prob": 0.05,
67
+ "max_length": 1876,
68
+ "max_speech_positions": 1876,
69
+ "max_text_positions": 600,
70
+ "model_type": "speecht5",
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_mel_bins": 80,
75
+ "pad_token_id": 1,
76
+ "positional_dropout": 0.1,
77
+ "reduction_factor": 2,
78
+ "scale_embedding": false,
79
+ "speaker_embedding_dim": 512,
80
+ "speech_decoder_postnet_dropout": 0.5,
81
+ "speech_decoder_postnet_kernel": 5,
82
+ "speech_decoder_postnet_layers": 5,
83
+ "speech_decoder_postnet_units": 256,
84
+ "speech_decoder_prenet_dropout": 0.5,
85
+ "speech_decoder_prenet_layers": 2,
86
+ "speech_decoder_prenet_units": 256,
87
+ "torch_dtype": "float32",
88
+ "transformers_version": "4.37.0.dev0",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 81
92
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20eb248a318996eb0ace1b788c8509e908c279754ac10d194b92dd2fad5b0050
3
+ size 577789320
runs/Jan09_16-22-57_5e7c64e924b5/events.out.tfevents.1704817385.5e7c64e924b5.7903.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02a9006bd5879155ec149441eac696069644471845008563c4b030f5546bcb4
3
+ size 6023
runs/Jan09_16-31-20_5e7c64e924b5/events.out.tfevents.1704817885.5e7c64e924b5.7903.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d6a2bc6db45bb963648353c5918ea80e1af51a04c0820f7cb9503b34b6cd82
3
+ size 6024
runs/Jan09_16-31-58_5e7c64e924b5/events.out.tfevents.1704817922.5e7c64e924b5.7903.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4ec7bafee6c66cc352502616848df9627d6dc0db3fb97e42ac3a79f24099fe
3
+ size 6024
runs/Jan09_16-32-14_5e7c64e924b5/events.out.tfevents.1704817937.5e7c64e924b5.7903.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8d11f500d1d7ccaf3a7df044d527937357aa8473014a1fd9bcaa1e8a94b582
3
+ size 6024
runs/Jan09_16-32-44_5e7c64e924b5/events.out.tfevents.1704817968.5e7c64e924b5.7903.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06710ba6249ae5ba86a15d4ad5862047c2d38603c2da189e38424b86bdfbc568
3
+ size 6024
runs/Jan09_16-33-17_5e7c64e924b5/events.out.tfevents.1704818000.5e7c64e924b5.7903.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cbb22452d2da48116fa4cfab171a73858bd75837ee2f826617692f9cf264636
3
+ size 6025
runs/Jan09_16-34-22_5e7c64e924b5/events.out.tfevents.1704818065.5e7c64e924b5.7903.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58338755f0331abdce6880bece9721495f083ddc54eda15de5d405299ba4765f
3
+ size 6023
runs/Jan09_16-38-35_5e7c64e924b5/events.out.tfevents.1704818318.5e7c64e924b5.7903.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99cb31752f129abd8ed2a45d738d3d2a57176778cce889d29896a3daed29329c
3
+ size 6023
runs/Jan09_16-39-18_5e7c64e924b5/events.out.tfevents.1704818361.5e7c64e924b5.7903.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2055396eadcb828f3c5109eff9783ea394ffebdf9a15b48101a0268840dc5ef
3
+ size 6023
runs/Jan09_16-39-36_5e7c64e924b5/events.out.tfevents.1704818379.5e7c64e924b5.7903.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08f0923b0d42d64d9eb7d0bd54e437b334390a91d493e630cb43b530b10249a
3
+ size 6023
runs/Jan09_16-43-26_5e7c64e924b5/events.out.tfevents.1704818610.5e7c64e924b5.7903.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592066d7bc08913d4863c83806d2b5c661a0bccec7e81ac2d0e0226a7ebe1a91
3
+ size 6023
runs/Jan09_16-53-59_5e7c64e924b5/events.out.tfevents.1704819243.5e7c64e924b5.7903.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6c310d12da216a997e73c6e1b352f324d856071f895fa84878b862649c7587
3
+ size 6024
runs/Jan09_16-54-39_5e7c64e924b5/events.out.tfevents.1704819282.5e7c64e924b5.7903.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8233f08541f27a2fec4a261da236e257cf195a072e42c4bd0c5aa69825908650
3
+ size 6024
runs/Jan09_16-55-07_5e7c64e924b5/events.out.tfevents.1704819311.5e7c64e924b5.7903.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91c1383c3f05c8c975ce4c5de378157bb6e647e8c9739c57e33d20bebbd3f69
3
+ size 6023
runs/Jan09_16-55-21_5e7c64e924b5/events.out.tfevents.1704819324.5e7c64e924b5.7903.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b688961f912de2288a34bdc192a50661dfb0f5793a170c993d050c6d637ddcbb
3
+ size 6024
runs/Jan09_16-55-41_5e7c64e924b5/events.out.tfevents.1704819344.5e7c64e924b5.7903.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29e30e2b39384510b3b5cb70fa7512420d3cafc52fbf5679356acf6766e6930
3
+ size 6023
runs/Jan09_17-00-57_5e7c64e924b5/events.out.tfevents.1704819669.5e7c64e924b5.7903.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c320f14b0e939257ebeee9cd57ae6b945644f5bed65cd09f2b0fc8c5cb6738
3
+ size 6023
runs/Jan09_17-11-44_5e7c64e924b5/events.out.tfevents.1704820308.5e7c64e924b5.7903.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c294cd98199c35c3b65c531ebdde2eb409e3edd2bd5a2a8094f0596e6edf3fda
3
+ size 12559
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
54
+ "eos_token": "</s>",
55
+ "mask_token": "<mask>",
56
+ "model_max_length": 600,
57
+ "normalize": false,
58
+ "pad_token": "<pad>",
59
+ "processor_class": "SpeechT5Processor",
60
+ "sp_model_kwargs": {},
61
+ "tokenizer_class": "SpeechT5Tokenizer",
62
+ "unk_token": "<unk>"
63
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700c8df6d8797f98393028b5a53b9b9754ae3d84d007c023b4be330128858aab
3
+ size 4856