Mehrdad-S commited on
Commit
bf35cd5
·
verified ·
1 Parent(s): 6c9f6e7

End of training

Browse files
Files changed (2) hide show
  1. README.md +100 -0
  2. generation_config.json +9 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: last_vc
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
+ # last_vc
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: 0.5195
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: 5e-06
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 64
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
+ - training_steps: 4000
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-------:|:----:|:---------------:|
53
+ | 0.7194 | 0.3820 | 100 | 0.6257 |
54
+ | 0.6475 | 0.7641 | 200 | 0.5903 |
55
+ | 0.622 | 1.1452 | 300 | 0.5744 |
56
+ | 0.6042 | 1.5272 | 400 | 0.5645 |
57
+ | 0.5932 | 1.9093 | 500 | 0.5568 |
58
+ | 0.5962 | 2.2904 | 600 | 0.5545 |
59
+ | 0.5877 | 2.6724 | 700 | 0.5494 |
60
+ | 0.572 | 3.0535 | 800 | 0.5465 |
61
+ | 0.5705 | 3.4355 | 900 | 0.5434 |
62
+ | 0.5698 | 3.8176 | 1000 | 0.5394 |
63
+ | 0.5661 | 4.1987 | 1100 | 0.5393 |
64
+ | 0.5569 | 4.5807 | 1200 | 0.5378 |
65
+ | 0.5627 | 4.9628 | 1300 | 0.5363 |
66
+ | 0.5596 | 5.3438 | 1400 | 0.5338 |
67
+ | 0.5581 | 5.7259 | 1500 | 0.5310 |
68
+ | 0.5542 | 6.1070 | 1600 | 0.5307 |
69
+ | 0.5483 | 6.4890 | 1700 | 0.5304 |
70
+ | 0.5536 | 6.8711 | 1800 | 0.5273 |
71
+ | 0.5595 | 7.2521 | 1900 | 0.5273 |
72
+ | 0.5448 | 7.6342 | 2000 | 0.5276 |
73
+ | 0.5429 | 8.0153 | 2100 | 0.5270 |
74
+ | 0.5507 | 8.3973 | 2200 | 0.5261 |
75
+ | 0.5511 | 8.7794 | 2300 | 0.5251 |
76
+ | 0.5501 | 9.1605 | 2400 | 0.5243 |
77
+ | 0.5434 | 9.5425 | 2500 | 0.5254 |
78
+ | 0.5434 | 9.9245 | 2600 | 0.5249 |
79
+ | 0.5477 | 10.3056 | 2700 | 0.5210 |
80
+ | 0.5455 | 10.6877 | 2800 | 0.5213 |
81
+ | 0.5412 | 11.0688 | 2900 | 0.5212 |
82
+ | 0.5416 | 11.4508 | 3000 | 0.5203 |
83
+ | 0.5417 | 11.8329 | 3100 | 0.5236 |
84
+ | 0.5361 | 12.2139 | 3200 | 0.5220 |
85
+ | 0.5411 | 12.5960 | 3300 | 0.5220 |
86
+ | 0.5446 | 12.9780 | 3400 | 0.5191 |
87
+ | 0.5415 | 13.3591 | 3500 | 0.5199 |
88
+ | 0.5426 | 13.7412 | 3600 | 0.5210 |
89
+ | 0.5391 | 14.1223 | 3700 | 0.5198 |
90
+ | 0.5418 | 14.5043 | 3800 | 0.5196 |
91
+ | 0.5437 | 14.8863 | 3900 | 0.5195 |
92
+ | 0.539 | 15.2674 | 4000 | 0.5195 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.47.0
98
+ - Pytorch 2.5.1+cu121
99
+ - Datasets 3.3.1
100
+ - Tokenizers 0.21.0
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": "4.47.0"
9
+ }