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
Model card Files
xet
Metrics Community
JBZhang2342 commited on
Commit
ce06adb
·
1 Parent(s): 33693e2

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -18
  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,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: 0.5189
24
 
25
  ## Model description
26
 
@@ -55,16 +52,16 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:-----:|:-----:|:---------------:|
58
- | 0.5395 | 16.0 | 1000 | 0.4726 |
59
- | 0.4727 | 32.0 | 2000 | 0.4819 |
60
- | 0.4513 | 48.0 | 3000 | 0.4871 |
61
- | 0.4526 | 64.0 | 4000 | 0.5006 |
62
- | 0.4474 | 80.0 | 5000 | 0.5022 |
63
- | 0.4147 | 96.0 | 6000 | 0.5039 |
64
- | 0.423 | 112.0 | 7000 | 0.5154 |
65
- | 0.4271 | 128.0 | 8000 | 0.5217 |
66
- | 0.4232 | 144.0 | 9000 | 0.5198 |
67
- | 0.4044 | 160.0 | 10000 | 0.5189 |
68
 
69
 
70
  ### 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: 0.4530
21
 
22
  ## Model description
23
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:-----:|:---------------:|
55
+ | 0.5188 | 3.9 | 1000 | 0.4639 |
56
+ | 0.4705 | 7.8 | 2000 | 0.4534 |
57
+ | 0.4559 | 11.7 | 3000 | 0.4463 |
58
+ | 0.4763 | 15.59 | 4000 | 0.4477 |
59
+ | 0.4549 | 19.49 | 5000 | 0.4474 |
60
+ | 0.4684 | 23.39 | 6000 | 0.4580 |
61
+ | 0.4471 | 27.29 | 7000 | 0.4468 |
62
+ | 0.4666 | 31.19 | 8000 | 0.4472 |
63
+ | 0.4338 | 35.09 | 9000 | 0.4515 |
64
+ | 0.4452 | 38.99 | 10000 | 0.4530 |
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8e9555320d1a780c3a88913046babb3624a1dacc5da0381f628454ab2639267
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6178b49908599563af03eb83d77b093a96815a4e5fa29d849ae2667107e0c2f
3
  size 577789320