Hugging Face's logo

Masternlp
/
tts

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
Metrics Community
Masternlp commited on
Commit
0fb7e03
·
verified ·
1 Parent(s): 42754b5

Masternlp

Browse files
Files changed (17) hide show
  1. README.md +81 -0
  2. added_tokens.json +4 -0
  3. config.json +92 -0
  4. generation_config.json +9 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +19 -0
  7. runs/Oct15_13-16-11_dc44ea559f9c/events.out.tfevents.1728998181.dc44ea559f9c.1013.0 +3 -0
  8. runs/Oct15_13-17-39_dc44ea559f9c/events.out.tfevents.1728998264.dc44ea559f9c.1013.1 +3 -0
  9. runs/Oct15_13-36-40_dc44ea559f9c/events.out.tfevents.1728999402.dc44ea559f9c.1013.2 +3 -0
  10. runs/Oct15_13-37-07_dc44ea559f9c/events.out.tfevents.1728999429.dc44ea559f9c.1013.3 +3 -0
  11. runs/Oct15_13-39-32_dc44ea559f9c/events.out.tfevents.1728999575.dc44ea559f9c.1013.4 +3 -0
  12. runs/Oct15_13-51-51_dc44ea559f9c/events.out.tfevents.1729000315.dc44ea559f9c.1013.5 +3 -0
  13. runs/Oct15_13-57-21_dc44ea559f9c/events.out.tfevents.1729000643.dc44ea559f9c.1013.6 +3 -0
  14. special_tokens_map.json +13 -0
  15. spm_char.model +3 -0
  16. tokenizer_config.json +63 -0
  17. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_feniks
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_feniks
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: 0.5319
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: 0.0001
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 200
47
+ - training_steps: 2000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.4478 | 3.0418 | 100 | 0.4543 |
55
+ | 0.4534 | 6.0837 | 200 | 0.4621 |
56
+ | 0.4373 | 9.1255 | 300 | 0.4543 |
57
+ | 0.4224 | 12.1673 | 400 | 0.4494 |
58
+ | 0.4127 | 15.2091 | 500 | 0.4657 |
59
+ | 0.4134 | 18.2510 | 600 | 0.4529 |
60
+ | 0.4047 | 21.2928 | 700 | 0.4724 |
61
+ | 0.3932 | 24.3346 | 800 | 0.4777 |
62
+ | 0.3907 | 27.3764 | 900 | 0.4942 |
63
+ | 0.3855 | 30.4183 | 1000 | 0.4870 |
64
+ | 0.3783 | 33.4601 | 1100 | 0.4860 |
65
+ | 0.3794 | 36.5019 | 1200 | 0.4867 |
66
+ | 0.3704 | 39.5437 | 1300 | 0.4965 |
67
+ | 0.3687 | 42.5856 | 1400 | 0.5151 |
68
+ | 0.3674 | 45.6274 | 1500 | 0.5165 |
69
+ | 0.3618 | 48.6692 | 1600 | 0.5377 |
70
+ | 0.3536 | 51.7110 | 1700 | 0.5206 |
71
+ | 0.3621 | 54.7529 | 1800 | 0.5419 |
72
+ | 0.3533 | 57.7947 | 1900 | 0.5337 |
73
+ | 0.3513 | 60.8365 | 2000 | 0.5319 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.44.2
79
+ - Pytorch 2.4.1+cu121
80
+ - Datasets 3.0.1
81
+ - Tokenizers 0.19.1
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": "4.44.2",
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": "4.44.2"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fec08511c6354314a5542168f69b941dfb903a93eca250f8e181c9ed8c4831
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/Oct15_13-16-11_dc44ea559f9c/events.out.tfevents.1728998181.dc44ea559f9c.1013.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f11d049b28f44a8e64d33592f489302344a8c5374ab13ae19428c0d5fd7fcc
3
+ size 6533
runs/Oct15_13-17-39_dc44ea559f9c/events.out.tfevents.1728998264.dc44ea559f9c.1013.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0ee23b18e6fd08a37f1889248234b5563ddf243bccac39aacab78fcf7424cd
3
+ size 6533
runs/Oct15_13-36-40_dc44ea559f9c/events.out.tfevents.1728999402.dc44ea559f9c.1013.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f1ee89904ee0710810718685d083e31e3f00b3a8ab7ff2c0e88212640ccae9
3
+ size 6533
runs/Oct15_13-37-07_dc44ea559f9c/events.out.tfevents.1728999429.dc44ea559f9c.1013.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a3b87b92963e220bd7c66ffba0658ac5258f08f7e81f55b2617beb7d6ecc073
3
+ size 6533
runs/Oct15_13-39-32_dc44ea559f9c/events.out.tfevents.1728999575.dc44ea559f9c.1013.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40313318700354c32d1177e88602f60b2ce134289869dc26db261f897a1d815
3
+ size 6533
runs/Oct15_13-51-51_dc44ea559f9c/events.out.tfevents.1729000315.dc44ea559f9c.1013.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283dd0662dea0476a1f161b4b5e926bcb7272bc10a02a72cf94bc86cd207d442
3
+ size 8256
runs/Oct15_13-57-21_dc44ea559f9c/events.out.tfevents.1729000643.dc44ea559f9c.1013.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4600ef77a62b673eda500bc351536d93cdbd7d7d03c1198f29516f009997e75
3
+ size 29163
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 sha256:0701b401f996d476c0ca6aa95f0477c25dc05b8e5be33ceff648204212990694
3
+ size 5368