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
29220f5
•
1 Parent(s): b4447cf

Model save

Browse files
Files changed (4) hide show
  1. README.md +46 -51
  2. model.safetensors +1 -1
  3. runs/Dec09_19-26-51_Threadripper/events.out.tfevents.1702168012.Threadripper +3 -0
  4. 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: 0.5139
24
 
25
  ## Model description
26
 
@@ -40,8 +35,8 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
- - train_batch_size: 2
44
- - eval_batch_size: 2
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -53,46 +48,46 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:-----:|:---------------:|
56
- | No log | 1.92 | 250 | 0.6150 |
57
- | 0.7483 | 3.85 | 500 | 0.5494 |
58
- | 0.7483 | 5.77 | 750 | 0.5001 |
59
- | 0.5482 | 7.69 | 1000 | 0.4861 |
60
- | 0.5482 | 9.62 | 1250 | 0.4792 |
61
- | 0.502 | 11.54 | 1500 | 0.4786 |
62
- | 0.502 | 13.46 | 1750 | 0.4804 |
63
- | 0.4794 | 15.38 | 2000 | 0.4803 |
64
- | 0.4794 | 17.31 | 2250 | 0.4724 |
65
- | 0.4685 | 19.23 | 2500 | 0.4801 |
66
- | 0.4685 | 21.15 | 2750 | 0.4740 |
67
- | 0.4553 | 23.08 | 3000 | 0.4840 |
68
- | 0.4553 | 25.0 | 3250 | 0.4857 |
69
- | 0.4567 | 26.92 | 3500 | 0.4792 |
70
- | 0.4567 | 28.85 | 3750 | 0.4831 |
71
- | 0.445 | 30.77 | 4000 | 0.4884 |
72
- | 0.445 | 32.69 | 4250 | 0.4845 |
73
- | 0.4412 | 34.62 | 4500 | 0.4944 |
74
- | 0.4412 | 36.54 | 4750 | 0.4940 |
75
- | 0.4373 | 38.46 | 5000 | 0.4863 |
76
- | 0.4373 | 40.38 | 5250 | 0.4899 |
77
- | 0.4353 | 42.31 | 5500 | 0.4954 |
78
- | 0.4353 | 44.23 | 5750 | 0.5005 |
79
- | 0.4265 | 46.15 | 6000 | 0.4994 |
80
- | 0.4265 | 48.08 | 6250 | 0.4918 |
81
- | 0.4285 | 50.0 | 6500 | 0.5022 |
82
- | 0.4285 | 51.92 | 6750 | 0.4939 |
83
- | 0.4209 | 53.85 | 7000 | 0.4989 |
84
- | 0.4209 | 55.77 | 7250 | 0.4959 |
85
- | 0.4206 | 57.69 | 7500 | 0.5013 |
86
- | 0.4206 | 59.62 | 7750 | 0.5061 |
87
- | 0.4189 | 61.54 | 8000 | 0.5092 |
88
- | 0.4189 | 63.46 | 8250 | 0.5084 |
89
- | 0.422 | 65.38 | 8500 | 0.5116 |
90
- | 0.422 | 67.31 | 8750 | 0.5115 |
91
- | 0.415 | 69.23 | 9000 | 0.5100 |
92
- | 0.415 | 71.15 | 9250 | 0.5121 |
93
- | 0.4179 | 73.08 | 9500 | 0.5112 |
94
- | 0.4179 | 75.0 | 9750 | 0.5115 |
95
- | 0.4139 | 76.92 | 10000 | 0.5139 |
96
 
97
 
98
  ### 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: 0.3797
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 1e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | No log | 2.34 | 250 | 0.5177 |
52
+ | 0.587 | 4.67 | 500 | 0.3719 |
53
+ | 0.587 | 7.01 | 750 | 0.3577 |
54
+ | 0.4026 | 9.35 | 1000 | 0.3580 |
55
+ | 0.4026 | 11.68 | 1250 | 0.3634 |
56
+ | 0.3733 | 14.02 | 1500 | 0.3597 |
57
+ | 0.3733 | 16.36 | 1750 | 0.3575 |
58
+ | 0.3643 | 18.69 | 2000 | 0.3580 |
59
+ | 0.3643 | 21.03 | 2250 | 0.3562 |
60
+ | 0.35 | 23.36 | 2500 | 0.3566 |
61
+ | 0.35 | 25.7 | 2750 | 0.3630 |
62
+ | 0.3433 | 28.04 | 3000 | 0.3551 |
63
+ | 0.3433 | 30.37 | 3250 | 0.3601 |
64
+ | 0.3412 | 32.71 | 3500 | 0.3648 |
65
+ | 0.3412 | 35.05 | 3750 | 0.3667 |
66
+ | 0.3377 | 37.38 | 4000 | 0.3716 |
67
+ | 0.3377 | 39.72 | 4250 | 0.3759 |
68
+ | 0.333 | 42.06 | 4500 | 0.3709 |
69
+ | 0.333 | 44.39 | 4750 | 0.3707 |
70
+ | 0.3319 | 46.73 | 5000 | 0.3722 |
71
+ | 0.3319 | 49.07 | 5250 | 0.3678 |
72
+ | 0.328 | 51.4 | 5500 | 0.3653 |
73
+ | 0.328 | 53.74 | 5750 | 0.3831 |
74
+ | 0.3235 | 56.07 | 6000 | 0.3731 |
75
+ | 0.3235 | 58.41 | 6250 | 0.3809 |
76
+ | 0.3241 | 60.75 | 6500 | 0.3791 |
77
+ | 0.3241 | 63.08 | 6750 | 0.3799 |
78
+ | 0.3197 | 65.42 | 7000 | 0.3759 |
79
+ | 0.3197 | 67.76 | 7250 | 0.3734 |
80
+ | 0.3202 | 70.09 | 7500 | 0.3717 |
81
+ | 0.3202 | 72.43 | 7750 | 0.3811 |
82
+ | 0.3189 | 74.77 | 8000 | 0.3821 |
83
+ | 0.3189 | 77.1 | 8250 | 0.3884 |
84
+ | 0.3177 | 79.44 | 8500 | 0.3811 |
85
+ | 0.3177 | 81.78 | 8750 | 0.3729 |
86
+ | 0.3162 | 84.11 | 9000 | 0.3803 |
87
+ | 0.3162 | 86.45 | 9250 | 0.3835 |
88
+ | 0.3154 | 88.79 | 9500 | 0.3845 |
89
+ | 0.3154 | 91.12 | 9750 | 0.3815 |
90
+ | 0.3143 | 93.46 | 10000 | 0.3797 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb7a5e3219ddee30b204cda407dd1738a177b4fa35d17340f482705f9b805055
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd52aa8323f242b94668a8a577835caa25e9bc9a798a1ab4c97153a579cdbc7
3
  size 577789320
runs/Dec09_19-26-51_Threadripper/events.out.tfevents.1702168012.Threadripper ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9affc00a50f283b493877deff3600681d9ec65c68a65e7ba8f41adeb45b206a8
3
+ size 20162
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8a87bba5354d1efeaadf95474ab859689b5fb40db4c87b65c38503165cc821a
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f6b2def9ba577d3825f85e8b5eecada59a187006f1a7157caed8116b45a86c
3
  size 4792