JBZhang2342 commited on
Commit
9663dae
1 Parent(s): da553f6

Model save

Browse files
README.md CHANGED
@@ -1,26 +1,21 @@
1
  ---
2
- language:
3
- - en
4
  license: mit
5
  base_model: microsoft/speecht5_tts
6
  tags:
7
- - en_accent,mozilla,t5,common_voice_1_0
8
  - generated_from_trainer
9
- datasets:
10
- - mozilla-foundation/common_voice_1_0
11
  model-index:
12
- - name: SpeechT5 TTS English Accented
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # SpeechT5 TTS English Accented
20
 
21
- This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.5093
24
 
25
  ## Model description
26
 
@@ -51,68 +46,68 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:------:|:-----:|:---------------:|
56
- | No log | 11.36 | 250 | 0.5773 |
57
- | 0.6817 | 22.73 | 500 | 0.4226 |
58
- | 0.6817 | 34.09 | 750 | 0.4172 |
59
- | 0.4227 | 45.45 | 1000 | 0.4403 |
60
- | 0.4227 | 56.82 | 1250 | 0.4363 |
61
- | 0.3798 | 68.18 | 1500 | 0.4678 |
62
- | 0.3798 | 79.55 | 1750 | 0.4609 |
63
- | 0.3629 | 90.91 | 2000 | 0.4706 |
64
- | 0.3629 | 102.27 | 2250 | 0.4558 |
65
- | 0.3534 | 113.64 | 2500 | 0.4697 |
66
- | 0.3534 | 125.0 | 2750 | 0.4641 |
67
- | 0.3429 | 136.36 | 3000 | 0.4813 |
68
- | 0.3429 | 147.73 | 3250 | 0.4933 |
69
- | 0.3354 | 159.09 | 3500 | 0.5028 |
70
- | 0.3354 | 170.45 | 3750 | 0.4860 |
71
- | 0.3247 | 181.82 | 4000 | 0.4945 |
72
- | 0.3247 | 193.18 | 4250 | 0.5021 |
73
- | 0.3227 | 204.55 | 4500 | 0.4802 |
74
- | 0.3227 | 215.91 | 4750 | 0.4874 |
75
- | 0.3173 | 227.27 | 5000 | 0.4917 |
76
- | 0.3173 | 238.64 | 5250 | 0.4913 |
77
- | 0.3124 | 250.0 | 5500 | 0.5010 |
78
- | 0.3124 | 261.36 | 5750 | 0.4846 |
79
- | 0.3044 | 272.73 | 6000 | 0.5064 |
80
- | 0.3044 | 284.09 | 6250 | 0.5071 |
81
- | 0.304 | 295.45 | 6500 | 0.5009 |
82
- | 0.304 | 306.82 | 6750 | 0.4901 |
83
- | 0.2991 | 318.18 | 7000 | 0.4887 |
84
- | 0.2991 | 329.55 | 7250 | 0.4908 |
85
- | 0.2981 | 340.91 | 7500 | 0.4866 |
86
- | 0.2981 | 352.27 | 7750 | 0.4972 |
87
- | 0.296 | 363.64 | 8000 | 0.5037 |
88
- | 0.296 | 375.0 | 8250 | 0.5099 |
89
- | 0.2956 | 386.36 | 8500 | 0.4939 |
90
- | 0.2956 | 397.73 | 8750 | 0.5055 |
91
- | 0.2895 | 409.09 | 9000 | 0.5012 |
92
- | 0.2895 | 420.45 | 9250 | 0.5231 |
93
- | 0.2918 | 431.82 | 9500 | 0.5082 |
94
- | 0.2918 | 443.18 | 9750 | 0.5120 |
95
- | 0.289 | 454.55 | 10000 | 0.5067 |
96
- | 0.289 | 465.91 | 10250 | 0.5097 |
97
- | 0.287 | 477.27 | 10500 | 0.5244 |
98
- | 0.287 | 488.64 | 10750 | 0.5116 |
99
- | 0.2836 | 500.0 | 11000 | 0.5073 |
100
- | 0.2836 | 511.36 | 11250 | 0.5089 |
101
- | 0.2864 | 522.73 | 11500 | 0.5145 |
102
- | 0.2864 | 534.09 | 11750 | 0.5077 |
103
- | 0.2831 | 545.45 | 12000 | 0.5006 |
104
- | 0.2831 | 556.82 | 12250 | 0.5145 |
105
- | 0.2824 | 568.18 | 12500 | 0.5124 |
106
- | 0.2824 | 579.55 | 12750 | 0.5166 |
107
- | 0.2836 | 590.91 | 13000 | 0.5174 |
108
- | 0.2836 | 602.27 | 13250 | 0.5082 |
109
- | 0.2814 | 613.64 | 13500 | 0.5157 |
110
- | 0.2814 | 625.0 | 13750 | 0.5210 |
111
- | 0.2813 | 636.36 | 14000 | 0.5161 |
112
- | 0.2813 | 647.73 | 14250 | 0.5092 |
113
- | 0.2804 | 659.09 | 14500 | 0.5131 |
114
- | 0.2804 | 670.45 | 14750 | 0.5128 |
115
- | 0.2796 | 681.82 | 15000 | 0.5093 |
116
 
117
 
118
  ### Framework versions
 
1
  ---
 
 
2
  license: mit
3
  base_model: microsoft/speecht5_tts
4
  tags:
 
5
  - generated_from_trainer
 
 
6
  model-index:
7
+ - name: speecht5_tts
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
+ # speecht5_tts
15
 
16
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.6650
19
 
20
  ## Model description
21
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | No log | 0.53 | 250 | 1.1630 |
52
+ | 1.3203 | 1.06 | 500 | 0.8518 |
53
+ | 1.3203 | 1.6 | 750 | 0.7785 |
54
+ | 0.8972 | 2.13 | 1000 | 0.7502 |
55
+ | 0.8972 | 2.66 | 1250 | 0.7369 |
56
+ | 0.8135 | 3.19 | 1500 | 0.7193 |
57
+ | 0.8135 | 3.72 | 1750 | 0.7152 |
58
+ | 0.777 | 4.26 | 2000 | 0.7082 |
59
+ | 0.777 | 4.79 | 2250 | 0.7076 |
60
+ | 0.7586 | 5.32 | 2500 | 0.6965 |
61
+ | 0.7586 | 5.85 | 2750 | 0.6894 |
62
+ | 0.747 | 6.38 | 3000 | 0.6790 |
63
+ | 0.747 | 6.91 | 3250 | 0.6858 |
64
+ | 0.7315 | 7.45 | 3500 | 0.6906 |
65
+ | 0.7315 | 7.98 | 3750 | 0.6687 |
66
+ | 0.7153 | 8.51 | 4000 | 0.6731 |
67
+ | 0.7153 | 9.04 | 4250 | 0.6732 |
68
+ | 0.7119 | 9.57 | 4500 | 0.6706 |
69
+ | 0.7119 | 10.11 | 4750 | 0.6648 |
70
+ | 0.6952 | 10.64 | 5000 | 0.6638 |
71
+ | 0.6952 | 11.17 | 5250 | 0.6652 |
72
+ | 0.6904 | 11.7 | 5500 | 0.6667 |
73
+ | 0.6904 | 12.23 | 5750 | 0.6629 |
74
+ | 0.6774 | 12.77 | 6000 | 0.6614 |
75
+ | 0.6774 | 13.3 | 6250 | 0.6644 |
76
+ | 0.6812 | 13.83 | 6500 | 0.6638 |
77
+ | 0.6812 | 14.36 | 6750 | 0.6621 |
78
+ | 0.6644 | 14.89 | 7000 | 0.6621 |
79
+ | 0.6644 | 15.43 | 7250 | 0.6604 |
80
+ | 0.6615 | 15.96 | 7500 | 0.6690 |
81
+ | 0.6615 | 16.49 | 7750 | 0.6540 |
82
+ | 0.6636 | 17.02 | 8000 | 0.6613 |
83
+ | 0.6636 | 17.55 | 8250 | 0.6637 |
84
+ | 0.6523 | 18.09 | 8500 | 0.6687 |
85
+ | 0.6523 | 18.62 | 8750 | 0.6582 |
86
+ | 0.6462 | 19.15 | 9000 | 0.6597 |
87
+ | 0.6462 | 19.68 | 9250 | 0.6586 |
88
+ | 0.6437 | 20.21 | 9500 | 0.6614 |
89
+ | 0.6437 | 20.74 | 9750 | 0.6627 |
90
+ | 0.6418 | 21.28 | 10000 | 0.6641 |
91
+ | 0.6418 | 21.81 | 10250 | 0.6633 |
92
+ | 0.6416 | 22.34 | 10500 | 0.6636 |
93
+ | 0.6416 | 22.87 | 10750 | 0.6623 |
94
+ | 0.6341 | 23.4 | 11000 | 0.6609 |
95
+ | 0.6341 | 23.94 | 11250 | 0.6615 |
96
+ | 0.6328 | 24.47 | 11500 | 0.6656 |
97
+ | 0.6328 | 25.0 | 11750 | 0.6609 |
98
+ | 0.6277 | 25.53 | 12000 | 0.6672 |
99
+ | 0.6277 | 26.06 | 12250 | 0.6636 |
100
+ | 0.6216 | 26.6 | 12500 | 0.6603 |
101
+ | 0.6216 | 27.13 | 12750 | 0.6673 |
102
+ | 0.6311 | 27.66 | 13000 | 0.6700 |
103
+ | 0.6311 | 28.19 | 13250 | 0.6616 |
104
+ | 0.6211 | 28.72 | 13500 | 0.6638 |
105
+ | 0.6211 | 29.26 | 13750 | 0.6610 |
106
+ | 0.6192 | 29.79 | 14000 | 0.6670 |
107
+ | 0.6192 | 30.32 | 14250 | 0.6679 |
108
+ | 0.6205 | 30.85 | 14500 | 0.6703 |
109
+ | 0.6205 | 31.38 | 14750 | 0.6636 |
110
+ | 0.6161 | 31.91 | 15000 | 0.6650 |
111
 
112
 
113
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f64ee5f5343b62635a8d6613b94cc68b6156fc48dc9d40579d079975fe4bbb
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44201dc52155467a3f7dd4afe63c3893418900d708f1e74008a48a6ff24d83da
3
  size 577789320
runs/Dec10_12-51-03_Threadripper/events.out.tfevents.1702230663.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01056a3f70d80d93298658b7a05c617c7dd43b8cc15ceae0ba565d58f6a19a71
3
+ size 27152
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c83d5c2a08b5dacb6a42f3094c7106f6ca6c49afb814c272693aaf3f990d0a0
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd5afd245304e4447817194e184643f69de32d52ca452dd9a2eea127f98ca01
3
  size 4792