Hugging Face's logo

Solo448
/
SpeechT5-fine-tune-en

Text-to-Audio
Transformers
TensorBoard
Safetensors
English
speecht5
English
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Solo448 commited on
Commit
ba77609
·
verified ·
1 Parent(s): c7a8fc3

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -9
  2. model.safetensors +1 -1
  3. runs/Oct20_05-25-35_21148bcaaf9a/events.out.tfevents.1729401939.21148bcaaf9a.1189.1 +2 -2
README.md CHANGED
@@ -21,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TTS_English_Technical_data dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.4500
25
 
26
  ## Model description
27
 
@@ -50,19 +50,20 @@ The following hyperparameters were used during training:
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 100
52
  - num_epochs: 3.0
 
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
- | 4.6741 | 0.3583 | 100 | 0.5122 |
59
- | 4.3722 | 0.7165 | 200 | 0.4912 |
60
- | 4.1313 | 1.0748 | 300 | 0.4727 |
61
- | 4.0803 | 1.4330 | 400 | 0.4687 |
62
- | 4.0268 | 1.7913 | 500 | 0.4604 |
63
- | 3.9039 | 2.1496 | 600 | 0.4581 |
64
- | 3.89 | 2.5078 | 700 | 0.4490 |
65
- | 3.9175 | 2.8661 | 800 | 0.4500 |
66
 
67
 
68
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TTS_English_Technical_data dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.4494
25
 
26
  ## Model description
27
 
 
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 100
52
  - num_epochs: 3.0
53
+ - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss |
58
  |:-------------:|:------:|:----:|:---------------:|
59
+ | 4.67 | 0.3583 | 100 | 0.5073 |
60
+ | 4.3667 | 0.7165 | 200 | 0.4967 |
61
+ | 4.1364 | 1.0748 | 300 | 0.4758 |
62
+ | 4.0266 | 1.4330 | 400 | 0.4679 |
63
+ | 4.0432 | 1.7913 | 500 | 0.4610 |
64
+ | 3.9342 | 2.1496 | 600 | 0.4603 |
65
+ | 3.906 | 2.5078 | 700 | 0.4531 |
66
+ | 3.8696 | 2.8661 | 800 | 0.4494 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d0ec921968e7bebc8cadead3ff853744c419e4aac832524b38842a2322ee1be
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e00476cb46ebc76746cc4ee7ea88968fa422b5dbbb804f9c2cfe520fe74bb03
3
  size 577789320
runs/Oct20_05-25-35_21148bcaaf9a/events.out.tfevents.1729401939.21148bcaaf9a.1189.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad7c7de4563763fbd46d240de87e94de13f0aff3c47ba2a9fd090405fc42be3
3
- size 15739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2899a01c51f59f594f274361c1e76c58907c4cacbfe9d88a1d45bf465073a5
3
+ size 16093