Hugging Face's logo

sil-ai
/
mzr-chapter-audio-dataset-force-aligned-speecht5

Text-to-Audio
Transformers
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
Community
woodwardmw commited on
Commit
1aa9ea5
·
verified ·
1 Parent(s): 58938a4

Model save

Browse files
Files changed (2) hide show
  1. README.md +101 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ykv-chapter-audio-dataset-force-aligned-speecht5
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
+ # ykv-chapter-audio-dataset-force-aligned-speecht5
16
+
17
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0562
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: 8
40
+ - eval_batch_size: 8
41
+ - seed: 3407
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 4000
47
+ - training_steps: 40000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:--------:|:-----:|:---------------:|
54
+ | 0.0899 | 12.5016 | 1000 | 0.0604 |
55
+ | 0.0742 | 25.0 | 2000 | 0.0540 |
56
+ | 0.073 | 37.5016 | 3000 | 0.0535 |
57
+ | 0.0733 | 50.0 | 4000 | 0.0561 |
58
+ | 0.0677 | 62.5016 | 5000 | 0.0530 |
59
+ | 0.0621 | 75.0 | 6000 | 0.0522 |
60
+ | 0.0652 | 87.5016 | 7000 | 0.0542 |
61
+ | 0.0609 | 100.0 | 8000 | 0.0527 |
62
+ | 0.0606 | 112.5016 | 9000 | 0.0530 |
63
+ | 0.059 | 125.0 | 10000 | 0.0528 |
64
+ | 0.0542 | 137.5016 | 11000 | 0.0529 |
65
+ | 0.0536 | 150.0 | 12000 | 0.0530 |
66
+ | 0.0543 | 162.5016 | 13000 | 0.0535 |
67
+ | 0.0547 | 175.0 | 14000 | 0.0539 |
68
+ | 0.0533 | 187.5016 | 15000 | 0.0539 |
69
+ | 0.0523 | 200.0 | 16000 | 0.0553 |
70
+ | 0.0506 | 212.5016 | 17000 | 0.0545 |
71
+ | 0.05 | 225.0 | 18000 | 0.0554 |
72
+ | 0.0509 | 237.5016 | 19000 | 0.0544 |
73
+ | 0.0474 | 250.0 | 20000 | 0.0550 |
74
+ | 0.0468 | 262.5016 | 21000 | 0.0548 |
75
+ | 0.0483 | 275.0 | 22000 | 0.0558 |
76
+ | 0.0477 | 287.5016 | 23000 | 0.0553 |
77
+ | 0.0471 | 300.0 | 24000 | 0.0553 |
78
+ | 0.0459 | 312.5016 | 25000 | 0.0559 |
79
+ | 0.0474 | 325.0 | 26000 | 0.0555 |
80
+ | 0.0452 | 337.5016 | 27000 | 0.0561 |
81
+ | 0.0445 | 350.0 | 28000 | 0.0558 |
82
+ | 0.0438 | 362.5016 | 29000 | 0.0560 |
83
+ | 0.0452 | 375.0 | 30000 | 0.0563 |
84
+ | 0.0438 | 387.5016 | 31000 | 0.0560 |
85
+ | 0.0437 | 400.0 | 32000 | 0.0563 |
86
+ | 0.0436 | 412.5016 | 33000 | 0.0563 |
87
+ | 0.0449 | 425.0 | 34000 | 0.0567 |
88
+ | 0.0434 | 437.5016 | 35000 | 0.0564 |
89
+ | 0.0448 | 450.0 | 36000 | 0.0563 |
90
+ | 0.0421 | 462.5016 | 37000 | 0.0562 |
91
+ | 0.0438 | 475.0 | 38000 | 0.0562 |
92
+ | 0.0429 | 487.5016 | 39000 | 0.0562 |
93
+ | 0.043 | 500.0 | 40000 | 0.0562 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.57.1
99
+ - Pytorch 2.8.0+cu128
100
+ - Datasets 4.2.0
101
+ - Tokenizers 0.22.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e94d7968644b656268e3bdf1d23bd1f33f89284dcdf9dc59561df9e487badf
3
  size 577899912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f8c503b2e02faa3670df636b8c49a13dd7558e2544d76d9ad24ad4b2f52979
3
  size 577899912