Hugging Face's logo

ptah23
/
speecht5_finetuned_voxpopuli_nl

Text-to-Audio
Transformers
PyTorch
TensorBoard
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ptah23 commited on
Commit
82812ca
•
1 Parent(s): 47b6187

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/speecht5_tts
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - voxpopuli
8
+ model-index:
9
+ - name: speecht5_finetuned_voxpopuli_nl
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # speecht5_finetuned_voxpopuli_nl
17
+
18
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4591
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - training_steps: 4000
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 0.7034 | 0.43 | 100 | 0.6427 |
55
+ | 0.6812 | 0.86 | 200 | 0.5998 |
56
+ | 0.5928 | 1.29 | 300 | 0.5292 |
57
+ | 0.5662 | 1.72 | 400 | 0.5095 |
58
+ | 0.5547 | 2.15 | 500 | 0.5024 |
59
+ | 0.5356 | 2.58 | 600 | 0.4929 |
60
+ | 0.532 | 3.01 | 700 | 0.4902 |
61
+ | 0.5312 | 3.44 | 800 | 0.4835 |
62
+ | 0.5171 | 3.87 | 900 | 0.4800 |
63
+ | 0.5178 | 4.3 | 1000 | 0.4780 |
64
+ | 0.5152 | 4.73 | 1100 | 0.4777 |
65
+ | 0.5064 | 5.16 | 1200 | 0.4737 |
66
+ | 0.5122 | 5.59 | 1300 | 0.4726 |
67
+ | 0.5042 | 6.02 | 1400 | 0.4700 |
68
+ | 0.5075 | 6.45 | 1500 | 0.4712 |
69
+ | 0.5057 | 6.88 | 1600 | 0.4688 |
70
+ | 0.5037 | 7.31 | 1700 | 0.4674 |
71
+ | 0.504 | 7.74 | 1800 | 0.4665 |
72
+ | 0.4977 | 8.17 | 1900 | 0.4652 |
73
+ | 0.4976 | 8.6 | 2000 | 0.4653 |
74
+ | 0.5014 | 9.03 | 2100 | 0.4650 |
75
+ | 0.4951 | 9.46 | 2200 | 0.4632 |
76
+ | 0.493 | 9.89 | 2300 | 0.4626 |
77
+ | 0.4983 | 10.32 | 2400 | 0.4628 |
78
+ | 0.4952 | 10.75 | 2500 | 0.4627 |
79
+ | 0.4961 | 11.18 | 2600 | 0.4616 |
80
+ | 0.4965 | 11.61 | 2700 | 0.4618 |
81
+ | 0.4895 | 12.04 | 2800 | 0.4615 |
82
+ | 0.4898 | 12.47 | 2900 | 0.4600 |
83
+ | 0.5008 | 12.9 | 3000 | 0.4614 |
84
+ | 0.4896 | 13.33 | 3100 | 0.4603 |
85
+ | 0.4957 | 13.76 | 3200 | 0.4612 |
86
+ | 0.4878 | 14.19 | 3300 | 0.4598 |
87
+ | 0.4923 | 14.62 | 3400 | 0.4594 |
88
+ | 0.4939 | 15.05 | 3500 | 0.4596 |
89
+ | 0.4828 | 15.48 | 3600 | 0.4591 |
90
+ | 0.4865 | 15.91 | 3700 | 0.4588 |
91
+ | 0.4999 | 16.34 | 3800 | 0.4600 |
92
+ | 0.4895 | 16.77 | 3900 | 0.4587 |
93
+ | 0.4929 | 17.2 | 4000 | 0.4591 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.31.0.dev0
99
+ - Pytorch 1.12.1+cu116
100
+ - Datasets 2.4.0
101
+ - Tokenizers 0.12.1