Hugging Face's logo

JBZhang2342
/
speecht5_tts

Text-to-Audio
Transformers
TensorBoard
Safetensors
English
speecht5
en_accent,mozilla,t5,common_voice_1_0
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JBZhang2342 commited on
Commit
f616197
•
1 Parent(s): 0b8466c

Model save

Browse files
Files changed (7) hide show
  1. README.md +47 -52
  2. model.safetensors +1 -1
  3. runs/Dec08_19-15-58_Threadripper/events.out.tfevents.1702080958.Threadripper +3 -0
  4. runs/Dec09_16-01-16_Threadripper/events.out.tfevents.1702155677.Threadripper +3 -0
  5. runs/Dec09_18-05-39_Threadripper/events.out.tfevents.1702163140.Threadripper +3 -0
  6. runs/Dec09_18-17-07_Threadripper/events.out.tfevents.1702163827.Threadripper +3 -0
  7. training_args.bin +1 -1
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: 0.4937
24
 
25
  ## Model description
26
 
@@ -51,53 +46,53 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:-----:|:-----:|:---------------:|
56
- | No log | 0.01 | 250 | 0.6600 |
57
- | 0.8131 | 0.01 | 500 | 0.6203 |
58
- | 0.8131 | 0.02 | 750 | 0.5819 |
59
- | 0.6493 | 0.03 | 1000 | 0.5436 |
60
- | 0.6493 | 0.03 | 1250 | 0.5372 |
61
- | 0.5998 | 0.04 | 1500 | 0.5411 |
62
- | 0.5998 | 0.04 | 1750 | 0.5351 |
63
- | 0.585 | 0.05 | 2000 | 0.5260 |
64
- | 0.585 | 0.06 | 2250 | 0.5254 |
65
- | 0.5778 | 0.06 | 2500 | 0.5217 |
66
- | 0.5778 | 0.07 | 2750 | 0.5229 |
67
- | 0.5667 | 0.07 | 3000 | 0.5115 |
68
- | 0.5667 | 0.08 | 3250 | 0.5143 |
69
- | 0.5692 | 0.09 | 3500 | 0.5143 |
70
- | 0.5692 | 0.09 | 3750 | 0.5130 |
71
- | 0.5607 | 0.1 | 4000 | 0.5082 |
72
- | 0.5607 | 0.11 | 4250 | 0.5141 |
73
- | 0.5601 | 0.11 | 4500 | 0.5103 |
74
- | 0.5601 | 0.12 | 4750 | 0.5065 |
75
- | 0.5569 | 0.12 | 5000 | 0.5048 |
76
- | 0.5569 | 0.13 | 5250 | 0.5018 |
77
- | 0.5552 | 0.14 | 5500 | 0.5006 |
78
- | 0.5552 | 0.14 | 5750 | 0.5074 |
79
- | 0.5548 | 0.15 | 6000 | 0.5045 |
80
- | 0.5548 | 0.16 | 6250 | 0.5021 |
81
- | 0.5563 | 0.16 | 6500 | 0.4996 |
82
- | 0.5563 | 0.17 | 6750 | 0.4982 |
83
- | 0.5527 | 0.17 | 7000 | 0.4982 |
84
- | 0.5527 | 0.18 | 7250 | 0.4996 |
85
- | 0.5448 | 0.19 | 7500 | 0.5005 |
86
- | 0.5448 | 0.19 | 7750 | 0.4988 |
87
- | 0.542 | 0.2 | 8000 | 0.4973 |
88
- | 0.542 | 0.21 | 8250 | 0.4969 |
89
- | 0.5491 | 0.21 | 8500 | 0.4985 |
90
- | 0.5491 | 0.22 | 8750 | 0.4953 |
91
- | 0.5392 | 0.23 | 9000 | 0.4956 |
92
- | 0.5392 | 0.23 | 9250 | 0.4988 |
93
- | 0.546 | 0.24 | 9500 | 0.4982 |
94
- | 0.546 | 0.24 | 9750 | 0.4968 |
95
- | 0.5396 | 0.25 | 10000 | 0.4937 |
96
 
97
 
98
  ### Framework versions
99
 
100
  - Transformers 4.36.0.dev0
101
  - Pytorch 2.1.0+cu121
102
- - Datasets 2.14.6
103
  - Tokenizers 0.14.1
 
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: 0.5154
19
 
20
  ## Model description
21
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:-----:|:---------------:|
51
+ | No log | 2.72 | 250 | 0.6947 |
52
+ | 0.7897 | 5.43 | 500 | 0.5278 |
53
+ | 0.7897 | 8.15 | 750 | 0.5005 |
54
+ | 0.5429 | 10.87 | 1000 | 0.4842 |
55
+ | 0.5429 | 13.59 | 1250 | 0.4830 |
56
+ | 0.4997 | 16.3 | 1500 | 0.4912 |
57
+ | 0.4997 | 19.02 | 1750 | 0.4820 |
58
+ | 0.4712 | 21.74 | 2000 | 0.4835 |
59
+ | 0.4712 | 24.46 | 2250 | 0.4840 |
60
+ | 0.4621 | 27.17 | 2500 | 0.4925 |
61
+ | 0.4621 | 29.89 | 2750 | 0.4855 |
62
+ | 0.4507 | 32.61 | 3000 | 0.4882 |
63
+ | 0.4507 | 35.33 | 3250 | 0.5065 |
64
+ | 0.4445 | 38.04 | 3500 | 0.5033 |
65
+ | 0.4445 | 40.76 | 3750 | 0.4991 |
66
+ | 0.4345 | 43.48 | 4000 | 0.4950 |
67
+ | 0.4345 | 46.2 | 4250 | 0.4986 |
68
+ | 0.4306 | 48.91 | 4500 | 0.5026 |
69
+ | 0.4306 | 51.63 | 4750 | 0.4986 |
70
+ | 0.4272 | 54.35 | 5000 | 0.5048 |
71
+ | 0.4272 | 57.07 | 5250 | 0.4967 |
72
+ | 0.4234 | 59.78 | 5500 | 0.5011 |
73
+ | 0.4234 | 62.5 | 5750 | 0.5017 |
74
+ | 0.4187 | 65.22 | 6000 | 0.5047 |
75
+ | 0.4187 | 67.93 | 6250 | 0.5041 |
76
+ | 0.4188 | 70.65 | 6500 | 0.5064 |
77
+ | 0.4188 | 73.37 | 6750 | 0.5164 |
78
+ | 0.4108 | 76.09 | 7000 | 0.5133 |
79
+ | 0.4108 | 78.8 | 7250 | 0.5086 |
80
+ | 0.4118 | 81.52 | 7500 | 0.5070 |
81
+ | 0.4118 | 84.24 | 7750 | 0.5093 |
82
+ | 0.4082 | 86.96 | 8000 | 0.5155 |
83
+ | 0.4082 | 89.67 | 8250 | 0.5089 |
84
+ | 0.407 | 92.39 | 8500 | 0.5134 |
85
+ | 0.407 | 95.11 | 8750 | 0.5056 |
86
+ | 0.407 | 97.83 | 9000 | 0.5154 |
87
+ | 0.407 | 100.54 | 9250 | 0.5108 |
88
+ | 0.4062 | 103.26 | 9500 | 0.5112 |
89
+ | 0.4062 | 105.98 | 9750 | 0.5122 |
90
+ | 0.4052 | 108.7 | 10000 | 0.5154 |
91
 
92
 
93
  ### Framework versions
94
 
95
  - Transformers 4.36.0.dev0
96
  - Pytorch 2.1.0+cu121
97
+ - Datasets 2.15.0
98
  - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c38312fd65393287c06d0ed9c61a2751c28847be22320233104e45e969642938
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40af692d6e3bb2d054401f50990a663c9ae6a81e31ebbf118cfa53f582092a8a
3
  size 577789320
runs/Dec08_19-15-58_Threadripper/events.out.tfevents.1702080958.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916e6847cbc666484dc740edb29ba144c012596c5bfa702cec8538ab3308efbb
3
+ size 5828
runs/Dec09_16-01-16_Threadripper/events.out.tfevents.1702155677.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b11aec6574f5e6b70c156775c4b3eb1aa91fc068a9464d96ba16bbcb8a790e3
3
+ size 5828
runs/Dec09_18-05-39_Threadripper/events.out.tfevents.1702163140.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43144f4322fee1f390cc9bb2aecc91d4cbce7e935eb6a3dfe36969192996ec3e
3
+ size 3650
runs/Dec09_18-17-07_Threadripper/events.out.tfevents.1702163827.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806fbcc7b7ff9d24f9da6c2bbd7f7c1065591c50b80752a1f71498db3a0b7eff
3
+ size 20162
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:776361c9301a15108722c06b3d0aa4b30194eab23009adfc90e46b41f8e14ae7
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3138df890605b117615e540fe95d0969dea01abff6c6f257d2e5a0a7a46c697f
3
  size 4792