Hugging Face's logo

kingmhd1519
/
Mehdi_Assamese_tts

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kingmhd1519 commited on
Commit
1ac462f
·
verified ·
1 Parent(s): 468fa5b

End of training

Browse files
Files changed (4) hide show
  1. README.md +104 -0
  2. generation_config.json +9 -0
  3. model.safetensors +1 -1
  4. runs/Dec21_05-17-11_9ba1faae5576/events.out.tfevents.1734758250.9ba1faae5576.2856.0 +2 -2
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: MEHDI_Assamese_TTS
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
+ # MEHDI_Assamese_TTS
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: 0.5555
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: 0.0002
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 32
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: 200
47
+ - num_epochs: 155
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:--------:|:----:|:---------------:|
54
+ | 1.2762 | 3.4561 | 100 | 0.5795 |
55
+ | 1.1771 | 6.9123 | 200 | 0.5489 |
56
+ | 1.1979 | 10.3509 | 300 | 0.5573 |
57
+ | 1.1083 | 13.8070 | 400 | 0.5319 |
58
+ | 1.0821 | 17.2456 | 500 | 0.5273 |
59
+ | 1.0297 | 20.7018 | 600 | 0.5075 |
60
+ | 1.0778 | 24.1404 | 700 | 0.5064 |
61
+ | 0.9818 | 27.5965 | 800 | 0.5098 |
62
+ | 0.9574 | 31.0351 | 900 | 0.4986 |
63
+ | 0.9571 | 34.4912 | 1000 | 0.5123 |
64
+ | 0.9955 | 37.9474 | 1100 | 0.5217 |
65
+ | 0.9455 | 41.3860 | 1200 | 0.5223 |
66
+ | 0.9084 | 44.8421 | 1300 | 0.5150 |
67
+ | 0.9057 | 48.2807 | 1400 | 0.5073 |
68
+ | 0.9038 | 51.7368 | 1500 | 0.5103 |
69
+ | 0.8802 | 55.1754 | 1600 | 0.5163 |
70
+ | 0.9033 | 58.6316 | 1700 | 0.5058 |
71
+ | 0.8507 | 62.0702 | 1800 | 0.5098 |
72
+ | 0.8549 | 65.5263 | 1900 | 0.5170 |
73
+ | 0.8795 | 68.9825 | 2000 | 0.5167 |
74
+ | 0.8629 | 72.4211 | 2100 | 0.5306 |
75
+ | 0.8577 | 75.8772 | 2200 | 0.5180 |
76
+ | 0.8197 | 79.3158 | 2300 | 0.5187 |
77
+ | 0.8278 | 82.7719 | 2400 | 0.5213 |
78
+ | 0.8016 | 86.2105 | 2500 | 0.5169 |
79
+ | 0.7927 | 89.6667 | 2600 | 0.5281 |
80
+ | 0.7815 | 93.1053 | 2700 | 0.5287 |
81
+ | 0.778 | 96.5614 | 2800 | 0.5288 |
82
+ | 0.7894 | 100.0 | 2900 | 0.5326 |
83
+ | 0.7521 | 103.4561 | 3000 | 0.5343 |
84
+ | 0.7705 | 106.9123 | 3100 | 0.5371 |
85
+ | 0.7652 | 110.3509 | 3200 | 0.5344 |
86
+ | 0.7458 | 113.8070 | 3300 | 0.5359 |
87
+ | 0.7583 | 117.2456 | 3400 | 0.5407 |
88
+ | 0.7479 | 120.7018 | 3500 | 0.5369 |
89
+ | 0.7338 | 124.1404 | 3600 | 0.5512 |
90
+ | 0.7662 | 127.5965 | 3700 | 0.5460 |
91
+ | 0.7212 | 131.0351 | 3800 | 0.5484 |
92
+ | 0.736 | 134.4912 | 3900 | 0.5447 |
93
+ | 0.7367 | 137.9474 | 4000 | 0.5536 |
94
+ | 0.7065 | 141.3860 | 4100 | 0.5566 |
95
+ | 0.711 | 144.8421 | 4200 | 0.5550 |
96
+ | 0.718 | 148.2807 | 4300 | 0.5555 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.47.1
102
+ - Pytorch 2.5.1+cu121
103
+ - Datasets 3.2.0
104
+ - 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": "4.47.1"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f94f115d0b456983ec694846dec9a5b760fc81ca421b5a26143f1772b3bb06d
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf17ffc1ca0caf7015b4d36eb6d41675f3b5b1b1b397ccef41b2bab4f00a3f6e
3
  size 577789320
runs/Dec21_05-17-11_9ba1faae5576/events.out.tfevents.1734758250.9ba1faae5576.2856.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a36e765540d57f5d553f7218fd92e6653059fefca76c4d57968558df95a69629
3
- size 54811
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da06f6bb973ed5d25c2216de35127145ab6063eb4dfcfa5ac8655b0ef503d487
3
+ size 55165