mikhail-panzo commited on
Commit
6e012ed
1 Parent(s): cd7e131

End of training

Browse files
Files changed (3) hide show
  1. README.md +76 -0
  2. generation_config.json +9 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/speecht5_tts
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: fil_b128_le5_s8000
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # fil_b128_le5_s8000
15
+
16
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4053
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 2000
46
+ - training_steps: 8000
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:--------:|:----:|:---------------:|
53
+ | 0.5575 | 43.4783 | 500 | 0.4795 |
54
+ | 0.4877 | 86.9565 | 1000 | 0.4371 |
55
+ | 0.4582 | 130.4348 | 1500 | 0.4196 |
56
+ | 0.4486 | 173.9130 | 2000 | 0.4145 |
57
+ | 0.4353 | 217.3913 | 2500 | 0.4096 |
58
+ | 0.4261 | 260.8696 | 3000 | 0.4057 |
59
+ | 0.4206 | 304.3478 | 3500 | 0.4049 |
60
+ | 0.4117 | 347.8261 | 4000 | 0.4065 |
61
+ | 0.4123 | 391.3043 | 4500 | 0.4029 |
62
+ | 0.4117 | 434.7826 | 5000 | 0.4046 |
63
+ | 0.4053 | 478.2609 | 5500 | 0.4045 |
64
+ | 0.4064 | 521.7391 | 6000 | 0.4047 |
65
+ | 0.4058 | 565.2174 | 6500 | 0.4042 |
66
+ | 0.3995 | 608.6957 | 7000 | 0.4058 |
67
+ | 0.4076 | 652.1739 | 7500 | 0.4054 |
68
+ | 0.4042 | 695.6522 | 8000 | 0.4053 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.41.0.dev0
74
+ - Pytorch 2.2.1+cu121
75
+ - Datasets 2.19.0
76
+ - Tokenizers 0.19.1
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": "4.41.0.dev0"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19d39dd9b619e7904c8275e5a7874baf72c3427e4b764352c5067cc1dc59a128
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49cbf05518972e8807c31c17f092139bf6b1e8ab98003caaa54d74d906f4eaa1
3
  size 577789320