Hugging Face's logo

Hawoly18
/
speecht5_tts_wolof

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Hawoly18 commited on
Commit
38e81ce
•
1 Parent(s): 87cc9ec

End of training

Browse files
Files changed (10) hide show
  1. README.md +141 -0
  2. added_tokens.json +4 -0
  3. config.json +92 -0
  4. generation_config.json +9 -0
  5. model.safetensors +3 -0
  6. runs/Oct22_13-42-05_8a27a372a7a9/events.out.tfevents.1729604538.8a27a372a7a9.30.0 +3 -0
  7. special_tokens_map.json +13 -0
  8. spm_char.model +3 -0
  9. tokenizer_config.json +63 -0
  10. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/speecht5_tts
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: speecht5_tts_wolof
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # speecht5_tts_wolof
16
+
17
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4769
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - training_steps: 4000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 2.1638 | 0.0963 | 50 | 1.0066 |
55
+ | 2.0092 | 0.1927 | 100 | 0.9555 |
56
+ | 1.7858 | 0.2890 | 150 | 0.9100 |
57
+ | 1.8592 | 0.3854 | 200 | 0.8772 |
58
+ | 1.778 | 0.4817 | 250 | 0.8337 |
59
+ | 1.6383 | 0.5780 | 300 | 0.7854 |
60
+ | 1.4971 | 0.6744 | 350 | 0.6216 |
61
+ | 1.2996 | 0.7707 | 400 | 0.5678 |
62
+ | 1.2728 | 0.8671 | 450 | 0.5555 |
63
+ | 1.2295 | 0.9634 | 500 | 0.5388 |
64
+ | 1.1974 | 1.0597 | 550 | 0.5332 |
65
+ | 1.1524 | 1.1561 | 600 | 0.5261 |
66
+ | 1.2034 | 1.2524 | 650 | 0.5243 |
67
+ | 1.1313 | 1.3487 | 700 | 0.5137 |
68
+ | 1.1011 | 1.4451 | 750 | 0.5121 |
69
+ | 1.1376 | 1.5414 | 800 | 0.5112 |
70
+ | 1.142 | 1.6378 | 850 | 0.5097 |
71
+ | 1.1685 | 1.7341 | 900 | 0.5035 |
72
+ | 1.122 | 1.8304 | 950 | 0.5030 |
73
+ | 1.117 | 1.9268 | 1000 | 0.5075 |
74
+ | 1.1164 | 2.0231 | 1050 | 0.5011 |
75
+ | 1.1186 | 2.1195 | 1100 | 0.4997 |
76
+ | 1.102 | 2.2158 | 1150 | 0.4999 |
77
+ | 1.0753 | 2.3121 | 1200 | 0.4995 |
78
+ | 1.0459 | 2.4085 | 1250 | 0.4950 |
79
+ | 1.1395 | 2.5048 | 1300 | 0.4967 |
80
+ | 1.086 | 2.6012 | 1350 | 0.4914 |
81
+ | 1.0647 | 2.6975 | 1400 | 0.4922 |
82
+ | 1.0779 | 2.7938 | 1450 | 0.4925 |
83
+ | 1.0814 | 2.8902 | 1500 | 0.4885 |
84
+ | 1.092 | 2.9865 | 1550 | 0.4909 |
85
+ | 1.0609 | 3.0829 | 1600 | 0.4883 |
86
+ | 1.0517 | 3.1792 | 1650 | 0.4903 |
87
+ | 1.0954 | 3.2755 | 1700 | 0.4886 |
88
+ | 1.0431 | 3.3719 | 1750 | 0.4903 |
89
+ | 1.0756 | 3.4682 | 1800 | 0.4914 |
90
+ | 1.0806 | 3.5645 | 1850 | 0.4835 |
91
+ | 1.0592 | 3.6609 | 1900 | 0.4891 |
92
+ | 1.054 | 3.7572 | 1950 | 0.4906 |
93
+ | 1.0297 | 3.8536 | 2000 | 0.4863 |
94
+ | 1.0461 | 3.9499 | 2050 | 0.4833 |
95
+ | 1.0244 | 4.0462 | 2100 | 0.4836 |
96
+ | 1.0341 | 4.1426 | 2150 | 0.4826 |
97
+ | 1.0287 | 4.2389 | 2200 | 0.4806 |
98
+ | 1.026 | 4.3353 | 2250 | 0.4831 |
99
+ | 1.0354 | 4.4316 | 2300 | 0.4850 |
100
+ | 1.0665 | 4.5279 | 2350 | 0.4824 |
101
+ | 1.0291 | 4.6243 | 2400 | 0.4800 |
102
+ | 1.0425 | 4.7206 | 2450 | 0.4791 |
103
+ | 1.0367 | 4.8170 | 2500 | 0.4796 |
104
+ | 1.0393 | 4.9133 | 2550 | 0.4814 |
105
+ | 1.0301 | 5.0096 | 2600 | 0.4799 |
106
+ | 1.0431 | 5.1060 | 2650 | 0.4790 |
107
+ | 1.0261 | 5.2023 | 2700 | 0.4791 |
108
+ | 1.05 | 5.2987 | 2750 | 0.4804 |
109
+ | 1.0296 | 5.3950 | 2800 | 0.4794 |
110
+ | 1.0296 | 5.4913 | 2850 | 0.4805 |
111
+ | 1.0214 | 5.5877 | 2900 | 0.4792 |
112
+ | 1.0277 | 5.6840 | 2950 | 0.4781 |
113
+ | 1.0355 | 5.7803 | 3000 | 0.4764 |
114
+ | 1.0325 | 5.8767 | 3050 | 0.4779 |
115
+ | 1.0206 | 5.9730 | 3100 | 0.4768 |
116
+ | 1.0316 | 6.0694 | 3150 | 0.4793 |
117
+ | 1.0426 | 6.1657 | 3200 | 0.4771 |
118
+ | 1.0562 | 6.2620 | 3250 | 0.4786 |
119
+ | 1.0242 | 6.3584 | 3300 | 0.4792 |
120
+ | 1.0144 | 6.4547 | 3350 | 0.4788 |
121
+ | 1.0335 | 6.5511 | 3400 | 0.4761 |
122
+ | 0.9995 | 6.6474 | 3450 | 0.4757 |
123
+ | 1.0119 | 6.7437 | 3500 | 0.4772 |
124
+ | 1.0355 | 6.8401 | 3550 | 0.4789 |
125
+ | 0.9858 | 6.9364 | 3600 | 0.4767 |
126
+ | 1.0327 | 7.0328 | 3650 | 0.4757 |
127
+ | 1.0355 | 7.1291 | 3700 | 0.4746 |
128
+ | 0.9974 | 7.2254 | 3750 | 0.4757 |
129
+ | 1.0296 | 7.3218 | 3800 | 0.4761 |
130
+ | 1.0033 | 7.4181 | 3850 | 0.4759 |
131
+ | 1.0013 | 7.5145 | 3900 | 0.4751 |
132
+ | 1.0086 | 7.6108 | 3950 | 0.4756 |
133
+ | 1.0191 | 7.7071 | 4000 | 0.4769 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.46.0.dev0
139
+ - Pytorch 2.4.0
140
+ - Datasets 3.0.1
141
+ - Tokenizers 0.20.0
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": 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": "4.46.0.dev0",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 81
92
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 1876,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.46.0.dev0"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91ef8f9031d4dd9eaa399011ca7c2731f72fcb5c2fee189c83febbaccdb919a
3
+ size 577789320
runs/Oct22_13-42-05_8a27a372a7a9/events.out.tfevents.1729604538.8a27a372a7a9.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce02d6b917662ae5981efdbee43342139602ddcb60e60a02d6da5cb60e2b3159
3
+ size 62415
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": false,
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:b4260b6cedfe0b082fce2bf0abf6e442288b523662fabd6509f51106a36618b9
3
+ size 5432