Hugging Face's logo

Predict9731
/
speecht5_tts_voxpopuli_cs

Text-to-Audio
Transformers
Safetensors
Czech
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
Predict9731 commited on
Commit
9a1739b
•
1 Parent(s): 1c1f9ad

Training in progress, step 1000

Browse files
Files changed (26) hide show
  1. added_tokens.json +4 -0
  2. config.json +92 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +19 -0
  5. runs/Dec06_22-20-25_Node202/events.out.tfevents.1701897625.Node202.804.0 +3 -0
  6. runs/Dec06_22-41-38_Node202/events.out.tfevents.1701898899.Node202.41656.0 +3 -0
  7. runs/Dec06_22-51-45_Node202/events.out.tfevents.1701899505.Node202.33784.0 +3 -0
  8. runs/Dec06_23-07-53_Node202/events.out.tfevents.1701900473.Node202.39024.0 +3 -0
  9. runs/Dec06_23-15-03_Node202/events.out.tfevents.1701900903.Node202.9296.0 +3 -0
  10. runs/Dec06_23-21-47_Node202/events.out.tfevents.1701901308.Node202.41372.0 +3 -0
  11. runs/Dec06_23-27-53_Node202/events.out.tfevents.1701901674.Node202.24820.0 +3 -0
  12. runs/Dec06_23-34-50_Node202/events.out.tfevents.1701902090.Node202.33932.0 +3 -0
  13. runs/Dec06_23-41-41_Node202/events.out.tfevents.1701902501.Node202.31372.0 +3 -0
  14. runs/Dec06_23-47-01_Node202/events.out.tfevents.1701902822.Node202.24848.0 +3 -0
  15. runs/Dec06_23-50-25_Node202/events.out.tfevents.1701903025.Node202.31468.0 +3 -0
  16. runs/Dec06_23-56-19_Node202/events.out.tfevents.1701903380.Node202.24836.0 +3 -0
  17. runs/Dec07_00-00-15_Node202/events.out.tfevents.1701903616.Node202.40688.0 +3 -0
  18. runs/Dec07_00-07-02_Node202/events.out.tfevents.1701904022.Node202.41620.0 +3 -0
  19. runs/Dec07_00-21-26_Node202/events.out.tfevents.1701904886.Node202.9672.0 +3 -0
  20. runs/Dec07_10-28-36_Node202/events.out.tfevents.1701941317.Node202.18176.0 +3 -0
  21. runs/Dec08_15-46-54_Node202/events.out.tfevents.1702046815.Node202.9628.0 +3 -0
  22. runs/Dec08_15-55-08_Node202/events.out.tfevents.1702047308.Node202.21936.0 +3 -0
  23. special_tokens_map.json +13 -0
  24. spm_char.model +3 -0
  25. tokenizer_config.json +63 -0
  26. 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": "4.36.0.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:d2d0abfafc3468e611e91719ce5801a10b79419a57a4386c10974066c7e51540
3
+ size 577789320
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "SpeechT5FeatureExtractor",
4
+ "feature_size": 1,
5
+ "fmax": 7600,
6
+ "fmin": 80,
7
+ "frame_signal_scale": 1.0,
8
+ "hop_length": 16,
9
+ "mel_floor": 1e-10,
10
+ "num_mel_bins": 80,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "processor_class": "SpeechT5Processor",
14
+ "reduction_factor": 2,
15
+ "return_attention_mask": true,
16
+ "sampling_rate": 16000,
17
+ "win_function": "hann_window",
18
+ "win_length": 64
19
+ }
runs/Dec06_22-20-25_Node202/events.out.tfevents.1701897625.Node202.804.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e800d8963b2f5860ea7a61bce0e440fad5ad8aecfdf562575a1b36b3322cd7
3
+ size 6021
runs/Dec06_22-41-38_Node202/events.out.tfevents.1701898899.Node202.41656.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de478d401d29025a61a54645e413d73b25c17d47f90afbcba9184c93176347f6
3
+ size 6021
runs/Dec06_22-51-45_Node202/events.out.tfevents.1701899505.Node202.33784.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0995397f2d713a3814f2c41283dcfd4fc6a1e16f31a7205a0348e6497e17e77
3
+ size 6021
runs/Dec06_23-07-53_Node202/events.out.tfevents.1701900473.Node202.39024.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4749b2d0956d9abc72dc530ec6313bb712cab6a682002566c09127a4095a2f41
3
+ size 6021
runs/Dec06_23-15-03_Node202/events.out.tfevents.1701900903.Node202.9296.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eae5a4c60c697c2e751f2193e56f83cc70fecc2d2a0b1f60d529c62516d6427
3
+ size 6021
runs/Dec06_23-21-47_Node202/events.out.tfevents.1701901308.Node202.41372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b6274703304b0ac8d38334195ccd4eb0575120233e03dd5214898099d43de2
3
+ size 6021
runs/Dec06_23-27-53_Node202/events.out.tfevents.1701901674.Node202.24820.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f4a87a855931b1f31e9352ad7e5f8a6b8d13b7636690735f7dc7c38e94f693
3
+ size 6020
runs/Dec06_23-34-50_Node202/events.out.tfevents.1701902090.Node202.33932.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bf21b9244373395d5750adf18cf36f6c1d13dc116acf40fa00418571c2777a
3
+ size 6021
runs/Dec06_23-41-41_Node202/events.out.tfevents.1701902501.Node202.31372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b08afcb2b30123d049c649a2ef9be7e6c819e77968337d64b297c14f5f3fede
3
+ size 6020
runs/Dec06_23-47-01_Node202/events.out.tfevents.1701902822.Node202.24848.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159d3b038682d247cd65314e8590bc97cd45ff0fcfe04ef3220533e6da81c081
3
+ size 6020
runs/Dec06_23-50-25_Node202/events.out.tfevents.1701903025.Node202.31468.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbabb9aa34da5965e1d37ffc82e8c1e6102d0aaa4f0c9e911d1e3903ed4fbf29
3
+ size 6020
runs/Dec06_23-56-19_Node202/events.out.tfevents.1701903380.Node202.24836.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a501db51c4c14ee5324d22da7a7ea57c3c51350a5a385e75c6f6c223d50fa6
3
+ size 6020
runs/Dec07_00-00-15_Node202/events.out.tfevents.1701903616.Node202.40688.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41109f23daae8e60a6f511b4c21c2c4638829a266d91c49e3466660b9d1dbc09
3
+ size 8674
runs/Dec07_00-07-02_Node202/events.out.tfevents.1701904022.Node202.41620.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378c7ea71924ce6c34117c74c7a772b7a0f8c59c19fe0c5d7f32616bf9329f77
3
+ size 12285
runs/Dec07_00-21-26_Node202/events.out.tfevents.1701904886.Node202.9672.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c1b03a3a7a9192a240643e8ca6f804ff6886f33df1af8eaca23603b00ee6a8
3
+ size 32563
runs/Dec07_10-28-36_Node202/events.out.tfevents.1701941317.Node202.18176.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751b8ae1b9dd738bcf741d9966e4b80d60f60facf016af6a5c140fefddac053c
3
+ size 7261
runs/Dec08_15-46-54_Node202/events.out.tfevents.1702046815.Node202.9628.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d47510ba83c95d545372eb485f011293a7f449cc6082a9e6d033372c364014
3
+ size 6013
runs/Dec08_15-55-08_Node202/events.out.tfevents.1702047308.Node202.21936.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d8c660d0a3c68b90f048e9795974e4198d0ba66c5e3d0528d3430c1240c7b1
3
+ size 12549
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 sha256:87f017ddd51643493a44500c1bdb6a1df8e266939aa9da2cab383469c0355432
3
+ size 4411