Hugging Face's logo

Keerthana1011
/
speecht5_tts_voxpopuli_nl

TensorBoard
Safetensors
speecht5
Model card Files Metrics Community
Keerthana1011 commited on
Commit
183c780
·
verified ·
1 Parent(s): 34a98f0

Training in progress, step 1000

Browse files
Files changed (7) hide show
  1. added_tokens.json +4 -4
  2. config.json +92 -92
  3. model.safetensors +1 -1
  4. runs/Dec17_17-03-33_DESKTOP-P60G785/events.out.tfevents.1734435213.DESKTOP-P60G785 +3 -0
  5. special_tokens_map.json +13 -13
  6. tokenizer_config.json +64 -64
  7. training_args.bin +1 -1
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "<ctc_blank>": 80,
3
- "<mask>": 79
4
- }
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79
4
+ }
config.json CHANGED
@@ -1,92 +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": 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
- }
 
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": 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": "4.48.0.dev0",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 81
92
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdb57f52f9c54ab626b7a4eee00ac7c34499e7cd27263ff9f433cbd0abf782a3
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73228cf779dc336ce08330411116f1b9380d5055087325b9684981975477bcd9
3
  size 577789320
runs/Dec17_17-03-33_DESKTOP-P60G785/events.out.tfevents.1734435213.DESKTOP-P60G785 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a3ce2e7ccbcda0323106fc309f34ced22952b157d841155db784d068506d75
3
+ size 15092
special_tokens_map.json CHANGED
@@ -1,13 +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
- }
 
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
+ }
tokenizer_config.json CHANGED
@@ -1,64 +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
- }
 
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d7c6a734e5ae2c9bbbf3a08b722921efb0b9a6f532d71ea747b5d9174c33b1e
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0163cdd36ffd4833277ab0daf3a997f4a151017973ff15b98803dcfe80a3eba9
3
  size 5496