JBZhang2342 commited on
Commit
d74058b
1 Parent(s): e581be9

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: 0.6698
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 | 0.7543 |
57
- | 0.7974 | 22.73 | 500 | 0.5421 |
58
- | 0.7974 | 34.09 | 750 | 0.5298 |
59
- | 0.5132 | 45.45 | 1000 | 0.5404 |
60
- | 0.5132 | 56.82 | 1250 | 0.5513 |
61
- | 0.4589 | 68.18 | 1500 | 0.5664 |
62
- | 0.4589 | 79.55 | 1750 | 0.5688 |
63
- | 0.4362 | 90.91 | 2000 | 0.6007 |
64
- | 0.4362 | 102.27 | 2250 | 0.5819 |
65
- | 0.4264 | 113.64 | 2500 | 0.5813 |
66
- | 0.4264 | 125.0 | 2750 | 0.6025 |
67
- | 0.4136 | 136.36 | 3000 | 0.6001 |
68
- | 0.4136 | 147.73 | 3250 | 0.5854 |
69
- | 0.4058 | 159.09 | 3500 | 0.6119 |
70
- | 0.4058 | 170.45 | 3750 | 0.6194 |
71
- | 0.3914 | 181.82 | 4000 | 0.6248 |
72
- | 0.3914 | 193.18 | 4250 | 0.6185 |
73
- | 0.3892 | 204.55 | 4500 | 0.6116 |
74
- | 0.3892 | 215.91 | 4750 | 0.6208 |
75
- | 0.3807 | 227.27 | 5000 | 0.6275 |
76
- | 0.3807 | 238.64 | 5250 | 0.6214 |
77
- | 0.378 | 250.0 | 5500 | 0.6209 |
78
- | 0.378 | 261.36 | 5750 | 0.6398 |
79
- | 0.3677 | 272.73 | 6000 | 0.6272 |
80
- | 0.3677 | 284.09 | 6250 | 0.6274 |
81
- | 0.3662 | 295.45 | 6500 | 0.6571 |
82
- | 0.3662 | 306.82 | 6750 | 0.6337 |
83
- | 0.3593 | 318.18 | 7000 | 0.6456 |
84
- | 0.3593 | 329.55 | 7250 | 0.6321 |
85
- | 0.3587 | 340.91 | 7500 | 0.6360 |
86
- | 0.3587 | 352.27 | 7750 | 0.6504 |
87
- | 0.3556 | 363.64 | 8000 | 0.6478 |
88
- | 0.3556 | 375.0 | 8250 | 0.6516 |
89
- | 0.3554 | 386.36 | 8500 | 0.6398 |
90
- | 0.3554 | 397.73 | 8750 | 0.6524 |
91
- | 0.3489 | 409.09 | 9000 | 0.6484 |
92
- | 0.3489 | 420.45 | 9250 | 0.6418 |
93
- | 0.3513 | 431.82 | 9500 | 0.6421 |
94
- | 0.3513 | 443.18 | 9750 | 0.6460 |
95
- | 0.3464 | 454.55 | 10000 | 0.6586 |
96
- | 0.3464 | 465.91 | 10250 | 0.6613 |
97
- | 0.3456 | 477.27 | 10500 | 0.6511 |
98
- | 0.3456 | 488.64 | 10750 | 0.6474 |
99
- | 0.3405 | 500.0 | 11000 | 0.6402 |
100
- | 0.3405 | 511.36 | 11250 | 0.6541 |
101
- | 0.3436 | 522.73 | 11500 | 0.6596 |
102
- | 0.3436 | 534.09 | 11750 | 0.6631 |
103
- | 0.3385 | 545.45 | 12000 | 0.6574 |
104
- | 0.3385 | 556.82 | 12250 | 0.6516 |
105
- | 0.3405 | 568.18 | 12500 | 0.6675 |
106
- | 0.3405 | 579.55 | 12750 | 0.6617 |
107
- | 0.3403 | 590.91 | 13000 | 0.6573 |
108
- | 0.3403 | 602.27 | 13250 | 0.6595 |
109
- | 0.336 | 613.64 | 13500 | 0.6625 |
110
- | 0.336 | 625.0 | 13750 | 0.6601 |
111
- | 0.3376 | 636.36 | 14000 | 0.6655 |
112
- | 0.3376 | 647.73 | 14250 | 0.6695 |
113
- | 0.3357 | 659.09 | 14500 | 0.6623 |
114
- | 0.3357 | 670.45 | 14750 | 0.6576 |
115
- | 0.3348 | 681.82 | 15000 | 0.6698 |
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: 0.4466
19
 
20
  ## Model description
21
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | No log | 0.33 | 250 | 0.6848 |
52
+ | 0.7756 | 0.66 | 500 | 0.5241 |
53
+ | 0.7756 | 0.99 | 750 | 0.4902 |
54
+ | 0.5506 | 1.33 | 1000 | 0.4789 |
55
+ | 0.5506 | 1.66 | 1250 | 0.4696 |
56
+ | 0.5237 | 1.99 | 1500 | 0.4657 |
57
+ | 0.5237 | 2.32 | 1750 | 0.4603 |
58
+ | 0.5008 | 2.65 | 2000 | 0.4620 |
59
+ | 0.5008 | 2.98 | 2250 | 0.4587 |
60
+ | 0.4914 | 3.32 | 2500 | 0.4543 |
61
+ | 0.4914 | 3.65 | 2750 | 0.4523 |
62
+ | 0.4896 | 3.98 | 3000 | 0.4547 |
63
+ | 0.4896 | 4.31 | 3250 | 0.4509 |
64
+ | 0.4817 | 4.64 | 3500 | 0.4496 |
65
+ | 0.4817 | 4.97 | 3750 | 0.4487 |
66
+ | 0.4762 | 5.31 | 4000 | 0.4480 |
67
+ | 0.4762 | 5.64 | 4250 | 0.4515 |
68
+ | 0.4741 | 5.97 | 4500 | 0.4432 |
69
+ | 0.4741 | 6.3 | 4750 | 0.4449 |
70
+ | 0.4703 | 6.63 | 5000 | 0.4478 |
71
+ | 0.4703 | 6.96 | 5250 | 0.4426 |
72
+ | 0.4649 | 7.29 | 5500 | 0.4445 |
73
+ | 0.4649 | 7.63 | 5750 | 0.4454 |
74
+ | 0.4642 | 7.96 | 6000 | 0.4491 |
75
+ | 0.4642 | 8.29 | 6250 | 0.4463 |
76
+ | 0.4638 | 8.62 | 6500 | 0.4447 |
77
+ | 0.4638 | 8.95 | 6750 | 0.4426 |
78
+ | 0.4588 | 9.28 | 7000 | 0.4417 |
79
+ | 0.4588 | 9.62 | 7250 | 0.4433 |
80
+ | 0.4571 | 9.95 | 7500 | 0.4454 |
81
+ | 0.4571 | 10.28 | 7750 | 0.4437 |
82
+ | 0.4559 | 10.61 | 8000 | 0.4462 |
83
+ | 0.4559 | 10.94 | 8250 | 0.4442 |
84
+ | 0.453 | 11.27 | 8500 | 0.4483 |
85
+ | 0.453 | 11.6 | 8750 | 0.4438 |
86
+ | 0.452 | 11.94 | 9000 | 0.4425 |
87
+ | 0.452 | 12.27 | 9250 | 0.4443 |
88
+ | 0.4518 | 12.6 | 9500 | 0.4428 |
89
+ | 0.4518 | 12.93 | 9750 | 0.4430 |
90
+ | 0.448 | 13.26 | 10000 | 0.4449 |
91
+ | 0.448 | 13.59 | 10250 | 0.4449 |
92
+ | 0.4481 | 13.93 | 10500 | 0.4470 |
93
+ | 0.4481 | 14.26 | 10750 | 0.4446 |
94
+ | 0.4453 | 14.59 | 11000 | 0.4465 |
95
+ | 0.4453 | 14.92 | 11250 | 0.4443 |
96
+ | 0.4466 | 15.25 | 11500 | 0.4447 |
97
+ | 0.4466 | 15.58 | 11750 | 0.4440 |
98
+ | 0.4454 | 15.92 | 12000 | 0.4447 |
99
+ | 0.4454 | 16.25 | 12250 | 0.4474 |
100
+ | 0.4426 | 16.58 | 12500 | 0.4461 |
101
+ | 0.4426 | 16.91 | 12750 | 0.4485 |
102
+ | 0.4452 | 17.24 | 13000 | 0.4477 |
103
+ | 0.4452 | 17.57 | 13250 | 0.4450 |
104
+ | 0.4406 | 17.9 | 13500 | 0.4496 |
105
+ | 0.4406 | 18.24 | 13750 | 0.4459 |
106
+ | 0.4424 | 18.57 | 14000 | 0.4458 |
107
+ | 0.4424 | 18.9 | 14250 | 0.4486 |
108
+ | 0.4402 | 19.23 | 14500 | 0.4475 |
109
+ | 0.4402 | 19.56 | 14750 | 0.4462 |
110
+ | 0.4393 | 19.89 | 15000 | 0.4466 |
111
 
112
 
113
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d779fd4cf584dc5a00656cfb539ee5680b51cc488337535569f6af5179c5da2a
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c506632cdc27295bdcb3c92905898b79d038baf01147bfa6e6c0ec953c28a328
3
  size 577789320
runs/Dec09_23-34-58_Threadripper/events.out.tfevents.1702182898.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15a733a06925dccca6de412eefbc925e649e16156693fc8a000fd0932af25b8
3
+ size 27152
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7d39253e80f5188b3ef7192c7fc7af3a3206aece4e632972600e0ac9fe53f75
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be655e3fbba9f4483f4a4cbb8ed6ae2a869bf8ba9436115fa188045a9194518c
3
  size 4792