Hugging Face's logo

tired-racoon
/
speecht5_finetuned_big_pop_rock_no_genres

TensorBoard
Safetensors
speecht5
Model card Files Metrics Community
tired-racoon commited on
Commit
3a424fe
•
1 Parent(s): d64b4f5

Training in progress, step 1000

Browse files
Files changed (18) 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/Nov09_14-57-09_My_TUF/events.out.tfevents.1731153452.My_TUF.21164.0 +3 -0
  6. runs/Nov09_15-37-45_My_TUF/events.out.tfevents.1731155895.My_TUF.21164.1 +3 -0
  7. runs/Nov09_15-54-41_My_TUF/events.out.tfevents.1731156895.My_TUF.21164.2 +3 -0
  8. runs/Nov09_15-55-32_My_TUF/events.out.tfevents.1731156940.My_TUF.21164.3 +3 -0
  9. runs/Nov09_15-56-35_My_TUF/events.out.tfevents.1731157007.My_TUF.21164.4 +3 -0
  10. runs/Nov09_15-57-47_My_TUF/events.out.tfevents.1731157077.My_TUF.21164.5 +3 -0
  11. runs/Nov09_20-04-00_My_TUF/events.out.tfevents.1731171862.My_TUF.21164.6 +3 -0
  12. runs/Nov09_20-07-50_My_TUF/events.out.tfevents.1731172076.My_TUF.21164.7 +3 -0
  13. runs/Nov09_20-18-44_My_TUF/events.out.tfevents.1731172726.My_TUF.21164.8 +3 -0
  14. runs/Nov09_20-28-05_My_TUF/events.out.tfevents.1731173338.My_TUF.21164.9 +3 -0
  15. special_tokens_map.json +13 -0
  16. spm_char.model +3 -0
  17. tokenizer_config.json +64 -0
  18. 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": "zaebee/speecht5_tts_common_ru",
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": null,
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": "4.47.0.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:d2a4f47a4c903e4c9c14924a21d410b75d29d91a2f397daf93d13fc1835e1335
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/Nov09_14-57-09_My_TUF/events.out.tfevents.1731153452.My_TUF.21164.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789e82b6aa8087918b6c0ea7232eb5d9ed47e71257b54adf4d0a0dfdc149d3bf
3
+ size 7391
runs/Nov09_15-37-45_My_TUF/events.out.tfevents.1731155895.My_TUF.21164.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a03ab6d109901b78cdbc3f4e3228d2c3073e0c7ab986208c610744a3b38e40
3
+ size 7391
runs/Nov09_15-54-41_My_TUF/events.out.tfevents.1731156895.My_TUF.21164.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce3f93ce55360cf6d353f75d195c38f7bfbd1628aa3b2441aa28642733c5b13
3
+ size 6712
runs/Nov09_15-55-32_My_TUF/events.out.tfevents.1731156940.My_TUF.21164.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185c37ace436b7680772d3ba6ce8c9b7dedc4fe6cb819af6fca14cc9a99199e5
3
+ size 6712
runs/Nov09_15-56-35_My_TUF/events.out.tfevents.1731157007.My_TUF.21164.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f9d3d6141de823de770da2409a3256819c3846ed41d0d613bb3ea5ce7ba0b0
3
+ size 6711
runs/Nov09_15-57-47_My_TUF/events.out.tfevents.1731157077.My_TUF.21164.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc605f380647e8114ebc1e13695801c734fc0472b945d0fd4920759ae8f0ea44
3
+ size 7392
runs/Nov09_20-04-00_My_TUF/events.out.tfevents.1731171862.My_TUF.21164.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774b822acc48efb9e30dccc110059f5b817c5e0b988869cf3d4e65432559c906
3
+ size 7392
runs/Nov09_20-07-50_My_TUF/events.out.tfevents.1731172076.My_TUF.21164.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4b585f3166b5d3b7db0079f18072eedad4d87b7aff2d319377e1198b3b8bce
3
+ size 7392
runs/Nov09_20-18-44_My_TUF/events.out.tfevents.1731172726.My_TUF.21164.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527d999cd735c22fa9baea7017a77f453c8e7fa54a5b38b906eaa5e237da82b3
3
+ size 7392
runs/Nov09_20-28-05_My_TUF/events.out.tfevents.1731173338.My_TUF.21164.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca1e0ef6b21ce55f0c34b552cc34f90a58eed088c615ca6602670a44c25554d
3
+ size 20542
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": true,
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 sha256:5f26c58d575eb204378aa56ede631c9845fedf0eb1778d505c78fb41d5acb91d
3
+ size 5496