Hugging Face's logo

Kishor798
/
speecht5_finetuned_2500

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Kishor798 commited on
Commit
d37568e
·
verified ·
1 Parent(s): a32050c

End of training

Browse files
Files changed (3) hide show
  1. README.md +39 -29
  2. model.safetensors +1 -1
  3. runs/Nov08_02-13-39_6a4f3c9bb569/events.out.tfevents.1731032032.6a4f3c9bb569.365.0 +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3911
20
 
21
  ## Model description
22
 
@@ -44,38 +44,48 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
- - training_steps: 2500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-------:|:----:|:---------------:|
54
- | 0.5981 | 2.7586 | 100 | 0.5373 |
55
- | 0.5211 | 5.5172 | 200 | 0.4836 |
56
- | 0.5034 | 8.2759 | 300 | 0.4801 |
57
- | 0.4627 | 11.0345 | 400 | 0.4625 |
58
- | 0.4494 | 13.7931 | 500 | 0.4718 |
59
- | 0.4344 | 16.5517 | 600 | 0.4308 |
60
- | 0.4352 | 19.3103 | 700 | 0.4549 |
61
- | 0.4036 | 22.0690 | 800 | 0.4363 |
62
- | 0.3965 | 24.8276 | 900 | 0.4118 |
63
- | 0.39 | 27.5862 | 1000 | 0.4093 |
64
- | 0.3792 | 30.3448 | 1100 | 0.4142 |
65
- | 0.37 | 33.1034 | 1200 | 0.4080 |
66
- | 0.3702 | 35.8621 | 1300 | 0.4032 |
67
- | 0.3667 | 38.6207 | 1400 | 0.4031 |
68
- | 0.3703 | 41.3793 | 1500 | 0.3997 |
69
- | 0.3647 | 44.1379 | 1600 | 0.3961 |
70
- | 0.3553 | 46.8966 | 1700 | 0.3985 |
71
- | 0.3506 | 49.6552 | 1800 | 0.4003 |
72
- | 0.3504 | 52.4138 | 1900 | 0.3952 |
73
- | 0.3361 | 55.1724 | 2000 | 0.3950 |
74
- | 0.346 | 57.9310 | 2100 | 0.3953 |
75
- | 0.3371 | 60.6897 | 2200 | 0.3948 |
76
- | 0.3447 | 63.4483 | 2300 | 0.3933 |
77
- | 0.3278 | 66.2069 | 2400 | 0.3910 |
78
- | 0.3373 | 68.9655 | 2500 | 0.3911 |
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7095
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 3500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:---------:|:----:|:---------------:|
54
+ | 0.584 | 88.8889 | 100 | 0.6268 |
55
+ | 0.4839 | 177.7778 | 200 | 0.5803 |
56
+ | 0.4304 | 266.6667 | 300 | 0.6589 |
57
+ | 0.3976 | 355.5556 | 400 | 0.6201 |
58
+ | 0.3594 | 444.4444 | 500 | 0.6107 |
59
+ | 0.3468 | 533.3333 | 600 | 0.6492 |
60
+ | 0.3353 | 622.2222 | 700 | 0.6362 |
61
+ | 0.3194 | 711.1111 | 800 | 0.6373 |
62
+ | 0.3065 | 800.0 | 900 | 0.6431 |
63
+ | 0.2985 | 888.8889 | 1000 | 0.6736 |
64
+ | 0.289 | 977.7778 | 1100 | 0.6697 |
65
+ | 0.2833 | 1066.6667 | 1200 | 0.7000 |
66
+ | 0.2798 | 1155.5556 | 1300 | 0.6875 |
67
+ | 0.2775 | 1244.4444 | 1400 | 0.7149 |
68
+ | 0.275 | 1333.3333 | 1500 | 0.6630 |
69
+ | 0.2722 | 1422.2222 | 1600 | 0.7117 |
70
+ | 0.2622 | 1511.1111 | 1700 | 0.6647 |
71
+ | 0.2481 | 1600.0 | 1800 | 0.6985 |
72
+ | 0.2474 | 1688.8889 | 1900 | 0.7020 |
73
+ | 0.2511 | 1777.7778 | 2000 | 0.6847 |
74
+ | 0.2359 | 1866.6667 | 2100 | 0.6940 |
75
+ | 0.2336 | 1955.5556 | 2200 | 0.6996 |
76
+ | 0.2338 | 2044.4444 | 2300 | 0.7134 |
77
+ | 0.23 | 2133.3333 | 2400 | 0.7031 |
78
+ | 0.2305 | 2222.2222 | 2500 | 0.6993 |
79
+ | 0.2273 | 2311.1111 | 2600 | 0.7099 |
80
+ | 0.2229 | 2400.0 | 2700 | 0.6907 |
81
+ | 0.2151 | 2488.8889 | 2800 | 0.6985 |
82
+ | 0.2232 | 2577.7778 | 2900 | 0.6972 |
83
+ | 0.2234 | 2666.6667 | 3000 | 0.7091 |
84
+ | 0.2165 | 2755.5556 | 3100 | 0.7103 |
85
+ | 0.2143 | 2844.4444 | 3200 | 0.7168 |
86
+ | 0.22 | 2933.3333 | 3300 | 0.6877 |
87
+ | 0.2225 | 3022.2222 | 3400 | 0.7050 |
88
+ | 0.2192 | 3111.1111 | 3500 | 0.7095 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a919ba62fbb9fd0b2b680924b5b84762dbbbfc99cc5ca505e6a5f1e7d09c916
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2163da3a65442b542cf86bbda3849d7d809c68827a5bcde216865fbce47d065
3
  size 577789320
runs/Nov08_02-13-39_6a4f3c9bb569/events.out.tfevents.1731032032.6a4f3c9bb569.365.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dae9e1d153fc7cfb09c95c70184e4f3f921541bae7576756cff25f83044f8d3e
3
- size 45557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cab93350f544cd6ec8ce7e527a9ffda10c6cd0a59026dbcd769cd3434aa667
3
+ size 45911