JBZhang2342 commited on
Commit
7c5b53d
1 Parent(s): 8626752

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: 0.7779
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 | 31.25 | 250 | 0.8090 |
57
- | 0.7576 | 62.5 | 500 | 0.6545 |
58
- | 0.7576 | 93.75 | 750 | 0.6266 |
59
- | 0.4719 | 125.0 | 1000 | 0.6372 |
60
- | 0.4719 | 156.25 | 1250 | 0.6317 |
61
- | 0.403 | 187.5 | 1500 | 0.6457 |
62
- | 0.403 | 218.75 | 1750 | 0.6571 |
63
- | 0.374 | 250.0 | 2000 | 0.6805 |
64
- | 0.374 | 281.25 | 2250 | 0.6814 |
65
- | 0.3564 | 312.5 | 2500 | 0.6814 |
66
- | 0.3564 | 343.75 | 2750 | 0.6956 |
67
- | 0.342 | 375.0 | 3000 | 0.6769 |
68
- | 0.342 | 406.25 | 3250 | 0.7000 |
69
- | 0.3339 | 437.5 | 3500 | 0.7052 |
70
- | 0.3339 | 468.75 | 3750 | 0.7104 |
71
- | 0.3205 | 500.0 | 4000 | 0.7095 |
72
- | 0.3205 | 531.25 | 4250 | 0.7120 |
73
- | 0.3112 | 562.5 | 4500 | 0.7194 |
74
- | 0.3112 | 593.75 | 4750 | 0.7363 |
75
- | 0.3045 | 625.0 | 5000 | 0.7252 |
76
- | 0.3045 | 656.25 | 5250 | 0.7003 |
77
- | 0.3067 | 687.5 | 5500 | 0.7176 |
78
- | 0.3067 | 718.75 | 5750 | 0.7513 |
79
- | 0.2938 | 750.0 | 6000 | 0.7403 |
80
- | 0.2938 | 781.25 | 6250 | 0.7180 |
81
- | 0.2894 | 812.5 | 6500 | 0.7569 |
82
- | 0.2894 | 843.75 | 6750 | 0.7398 |
83
- | 0.2886 | 875.0 | 7000 | 0.7384 |
84
- | 0.2886 | 906.25 | 7250 | 0.7363 |
85
- | 0.2877 | 937.5 | 7500 | 0.7550 |
86
- | 0.2877 | 968.75 | 7750 | 0.7350 |
87
- | 0.2822 | 1000.0 | 8000 | 0.8012 |
88
- | 0.2822 | 1031.25 | 8250 | 0.7509 |
89
- | 0.2808 | 1062.5 | 8500 | 0.7544 |
90
- | 0.2808 | 1093.75 | 8750 | 0.7851 |
91
- | 0.2746 | 1125.0 | 9000 | 0.7283 |
92
- | 0.2746 | 1156.25 | 9250 | 0.7559 |
93
- | 0.27 | 1187.5 | 9500 | 0.7449 |
94
- | 0.27 | 1218.75 | 9750 | 0.7496 |
95
- | 0.2693 | 1250.0 | 10000 | 0.7375 |
96
- | 0.2693 | 1281.25 | 10250 | 0.7723 |
97
- | 0.2674 | 1312.5 | 10500 | 0.7632 |
98
- | 0.2674 | 1343.75 | 10750 | 0.7825 |
99
- | 0.2678 | 1375.0 | 11000 | 0.7645 |
100
- | 0.2678 | 1406.25 | 11250 | 0.7502 |
101
- | 0.269 | 1437.5 | 11500 | 0.7762 |
102
- | 0.269 | 1468.75 | 11750 | 0.7500 |
103
- | 0.2642 | 1500.0 | 12000 | 0.7503 |
104
- | 0.2642 | 1531.25 | 12250 | 0.7460 |
105
- | 0.2618 | 1562.5 | 12500 | 0.7512 |
106
- | 0.2618 | 1593.75 | 12750 | 0.7889 |
107
- | 0.2642 | 1625.0 | 13000 | 0.7578 |
108
- | 0.2642 | 1656.25 | 13250 | 0.7678 |
109
- | 0.2628 | 1687.5 | 13500 | 0.7638 |
110
- | 0.2628 | 1718.75 | 13750 | 0.7721 |
111
- | 0.2612 | 1750.0 | 14000 | 0.7531 |
112
- | 0.2612 | 1781.25 | 14250 | 0.7924 |
113
- | 0.2555 | 1812.5 | 14500 | 0.7882 |
114
- | 0.2555 | 1843.75 | 14750 | 0.7841 |
115
- | 0.2596 | 1875.0 | 15000 | 0.7779 |
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: 0.5093
19
 
20
  ## Model description
21
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:-----:|:---------------:|
51
+ | No log | 11.36 | 250 | 0.5773 |
52
+ | 0.6817 | 22.73 | 500 | 0.4226 |
53
+ | 0.6817 | 34.09 | 750 | 0.4172 |
54
+ | 0.4227 | 45.45 | 1000 | 0.4403 |
55
+ | 0.4227 | 56.82 | 1250 | 0.4363 |
56
+ | 0.3798 | 68.18 | 1500 | 0.4678 |
57
+ | 0.3798 | 79.55 | 1750 | 0.4609 |
58
+ | 0.3629 | 90.91 | 2000 | 0.4706 |
59
+ | 0.3629 | 102.27 | 2250 | 0.4558 |
60
+ | 0.3534 | 113.64 | 2500 | 0.4697 |
61
+ | 0.3534 | 125.0 | 2750 | 0.4641 |
62
+ | 0.3429 | 136.36 | 3000 | 0.4813 |
63
+ | 0.3429 | 147.73 | 3250 | 0.4933 |
64
+ | 0.3354 | 159.09 | 3500 | 0.5028 |
65
+ | 0.3354 | 170.45 | 3750 | 0.4860 |
66
+ | 0.3247 | 181.82 | 4000 | 0.4945 |
67
+ | 0.3247 | 193.18 | 4250 | 0.5021 |
68
+ | 0.3227 | 204.55 | 4500 | 0.4802 |
69
+ | 0.3227 | 215.91 | 4750 | 0.4874 |
70
+ | 0.3173 | 227.27 | 5000 | 0.4917 |
71
+ | 0.3173 | 238.64 | 5250 | 0.4913 |
72
+ | 0.3124 | 250.0 | 5500 | 0.5010 |
73
+ | 0.3124 | 261.36 | 5750 | 0.4846 |
74
+ | 0.3044 | 272.73 | 6000 | 0.5064 |
75
+ | 0.3044 | 284.09 | 6250 | 0.5071 |
76
+ | 0.304 | 295.45 | 6500 | 0.5009 |
77
+ | 0.304 | 306.82 | 6750 | 0.4901 |
78
+ | 0.2991 | 318.18 | 7000 | 0.4887 |
79
+ | 0.2991 | 329.55 | 7250 | 0.4908 |
80
+ | 0.2981 | 340.91 | 7500 | 0.4866 |
81
+ | 0.2981 | 352.27 | 7750 | 0.4972 |
82
+ | 0.296 | 363.64 | 8000 | 0.5037 |
83
+ | 0.296 | 375.0 | 8250 | 0.5099 |
84
+ | 0.2956 | 386.36 | 8500 | 0.4939 |
85
+ | 0.2956 | 397.73 | 8750 | 0.5055 |
86
+ | 0.2895 | 409.09 | 9000 | 0.5012 |
87
+ | 0.2895 | 420.45 | 9250 | 0.5231 |
88
+ | 0.2918 | 431.82 | 9500 | 0.5082 |
89
+ | 0.2918 | 443.18 | 9750 | 0.5120 |
90
+ | 0.289 | 454.55 | 10000 | 0.5067 |
91
+ | 0.289 | 465.91 | 10250 | 0.5097 |
92
+ | 0.287 | 477.27 | 10500 | 0.5244 |
93
+ | 0.287 | 488.64 | 10750 | 0.5116 |
94
+ | 0.2836 | 500.0 | 11000 | 0.5073 |
95
+ | 0.2836 | 511.36 | 11250 | 0.5089 |
96
+ | 0.2864 | 522.73 | 11500 | 0.5145 |
97
+ | 0.2864 | 534.09 | 11750 | 0.5077 |
98
+ | 0.2831 | 545.45 | 12000 | 0.5006 |
99
+ | 0.2831 | 556.82 | 12250 | 0.5145 |
100
+ | 0.2824 | 568.18 | 12500 | 0.5124 |
101
+ | 0.2824 | 579.55 | 12750 | 0.5166 |
102
+ | 0.2836 | 590.91 | 13000 | 0.5174 |
103
+ | 0.2836 | 602.27 | 13250 | 0.5082 |
104
+ | 0.2814 | 613.64 | 13500 | 0.5157 |
105
+ | 0.2814 | 625.0 | 13750 | 0.5210 |
106
+ | 0.2813 | 636.36 | 14000 | 0.5161 |
107
+ | 0.2813 | 647.73 | 14250 | 0.5092 |
108
+ | 0.2804 | 659.09 | 14500 | 0.5131 |
109
+ | 0.2804 | 670.45 | 14750 | 0.5128 |
110
+ | 0.2796 | 681.82 | 15000 | 0.5093 |
111
 
112
 
113
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8f5df2ffd8e472536b1c6d19bb3a4fd8151efa01cf9a7a14e9d9ff0f416d55d
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f64ee5f5343b62635a8d6613b94cc68b6156fc48dc9d40579d079975fe4bbb
3
  size 577789320
runs/Dec10_12-04-47_Threadripper/events.out.tfevents.1702227887.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91a37218f9b94f1e28cf803cf703ad19dafa94fd14f751b9808bec68a24aecb
3
+ size 27152
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d9dd7b9b67c72cf7a396e9c4141f78737698ac6a5c33ff7a3224f25e46e2f39
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c83d5c2a08b5dacb6a42f3094c7106f6ca6c49afb814c272693aaf3f990d0a0
3
  size 4792