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
6f21a40
•
1 Parent(s): 0ae1f42

Model save

Browse files
Files changed (3) hide show
  1. README.md +16 -19
  2. model.safetensors +1 -1
  3. runs/Nov18_15-20-32_yifanhua-threadripper/events.out.tfevents.1700338832.yifanhua-threadripper +2 -2
README.md CHANGED
@@ -1,26 +1,23 @@
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: 0.4813
24
 
25
  ## Model description
26
 
@@ -39,7 +36,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 2e-05
43
  - train_batch_size: 10
44
  - eval_batch_size: 10
45
  - seed: 42
@@ -53,16 +50,16 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:-----:|:---------------:|
56
- | 0.5466 | 1.25 | 1000 | 0.5218 |
57
- | 0.5436 | 2.5 | 2000 | 0.5038 |
58
- | 0.5235 | 3.75 | 3000 | 0.4951 |
59
- | 0.5255 | 5.0 | 4000 | 0.4888 |
60
- | 0.4962 | 6.25 | 5000 | 0.4869 |
61
- | 0.5068 | 7.5 | 6000 | 0.4839 |
62
- | 0.4861 | 8.75 | 7000 | 0.4820 |
63
- | 0.5265 | 10.0 | 8000 | 0.4826 |
64
- | 0.4934 | 11.25 | 9000 | 0.4838 |
65
- | 0.5128 | 12.5 | 10000 | 0.4813 |
66
 
67
 
68
  ### Framework versions
 
1
  ---
 
 
2
  license: mit
3
  base_model: microsoft/speecht5_tts
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
+ - common_voice_13_0
8
  model-index:
9
+ - name: speecht5_tts
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # speecht5_tts
17
 
18
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_13_0 dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4825
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
  - train_batch_size: 10
41
  - eval_batch_size: 10
42
  - seed: 42
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
+ | 0.6559 | 1.0 | 1000 | 0.5323 |
54
+ | 0.6126 | 2.0 | 2000 | 0.5088 |
55
+ | 0.4919 | 3.0 | 3000 | 0.4990 |
56
+ | 0.5709 | 4.0 | 4000 | 0.4955 |
57
+ | 0.5827 | 5.0 | 5000 | 0.4907 |
58
+ | 0.5065 | 6.0 | 6000 | 0.4876 |
59
+ | 0.5181 | 7.0 | 7000 | 0.4862 |
60
+ | 0.5232 | 8.0 | 8000 | 0.4849 |
61
+ | 0.5159 | 9.0 | 9000 | 0.4835 |
62
+ | 0.5194 | 10.0 | 10000 | 0.4825 |
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8372fe5c7de46405d58c97a426d59cd503b05576fc9cf83023a93ea98e283f15
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f38f1427e82eb05c3735523555537731d1018a37b555e49287a41e33d800f05
3
  size 577789320
runs/Nov18_15-20-32_yifanhua-threadripper/events.out.tfevents.1700338832.yifanhua-threadripper CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5209b56e273a0014ba2585c17ed453339304ec363a97ed38f41f4b94370689ee
3
- size 195516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd06a45fb49dc162d53efe899c01a909bd1d42598d716c51ad3095c80a73964
3
+ size 322825