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
c764198
•
1 Parent(s): 648b4a2

Model save

Browse files
Files changed (2) hide show
  1. README.md +13 -16
  2. model.safetensors +1 -1
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,vocpopuli,t5
8
  - generated_from_trainer
9
  datasets:
10
- - facebook/voxpopuli
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 VoxPopuli dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.6988
24
 
25
  ## Model description
26
 
@@ -40,11 +37,11 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
- - train_batch_size: 6
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - gradient_accumulation_steps: 2
47
- - total_train_batch_size: 12
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 500
@@ -53,12 +50,12 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss |
57
- |:-------------:|:------:|:----:|:---------------:|
58
- | 0.4211 | 222.22 | 1000 | 0.6265 |
59
- | 0.4094 | 444.44 | 2000 | 0.6595 |
60
- | 0.3729 | 666.67 | 3000 | 0.7037 |
61
- | 0.365 | 888.89 | 4000 | 0.6988 |
62
 
63
 
64
  ### Framework versions
 
1
  ---
 
 
2
  license: mit
3
  base_model: microsoft/speecht5_tts
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
+ - common_voice_1_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_1_0 dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4868
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 1e-05
40
+ - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.5417 | 8.0 | 1000 | 0.4919 |
56
+ | 0.4956 | 16.0 | 2000 | 0.4833 |
57
+ | 0.4774 | 24.0 | 3000 | 0.4824 |
58
+ | 0.482 | 32.0 | 4000 | 0.4868 |
59
 
60
 
61
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2d9f946311df4e943aae5253613bc2ec07a25b2a1fdc60d1e74846240347455
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985affab59a0ae787cd6d8508249281bb0e50122c50c0909f9b7a4abbc7f667b
3
  size 577789320