Hugging Face's logo

JackismyShephard
/
speecht5_tts-finetuned-nst-da

Text-to-Speech
Transformers
TensorBoard
Safetensors
Danish
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JackismyShephard commited on
Commit
1a24b26
·
1 Parent(s): 93b2b84

train with reduced dataset using mcd as metric

Browse files
Files changed (6) hide show
  1. README.md +27 -23
  2. model.safetensors +1 -1
  3. runs/Feb15_13-20-07_CDT-DESKTOP-LINUX/events.out.tfevents.1707999610.CDT-DESKTOP-LINUX.28602.0 +3 -0
  4. runs/Feb15_14-00-58_CDT-DESKTOP-LINUX/events.out.tfevents.1708002061.CDT-DESKTOP-LINUX.29532.0 +3 -0
  5. runs/Feb15_14-12-26_CDT-DESKTOP-LINUX/events.out.tfevents.1708002746.CDT-DESKTOP-LINUX.30252.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -19,7 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the NST Danish ASR Database dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.3298
 
 
 
 
23
 
24
  ## Model description
25
 
@@ -49,28 +53,28 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-----:|:------:|:---------------:|
54
- | 0.3762 | 1.0 | 9429 | 0.3670 |
55
- | 0.3596 | 2.0 | 18858 | 0.3577 |
56
- | 0.3498 | 3.0 | 28287 | 0.3535 |
57
- | 0.3356 | 4.0 | 37716 | 0.3414 |
58
- | 0.3405 | 5.0 | 47145 | 0.3378 |
59
- | 0.3312 | 6.0 | 56574 | 0.3397 |
60
- | 0.3326 | 7.0 | 66003 | 0.3377 |
61
- | 0.3299 | 8.0 | 75432 | 0.3384 |
62
- | 0.3279 | 9.0 | 84861 | 0.3363 |
63
- | 0.3203 | 10.0 | 94290 | 0.3335 |
64
- | 0.3235 | 11.0 | 103719 | 0.3367 |
65
- | 0.3188 | 12.0 | 113148 | 0.3365 |
66
- | 0.3141 | 13.0 | 122577 | 0.3324 |
67
- | 0.3176 | 14.0 | 132006 | 0.3345 |
68
- | 0.3221 | 15.0 | 141435 | 0.3331 |
69
- | 0.3157 | 16.0 | 150864 | 0.3317 |
70
- | 0.314 | 17.0 | 160293 | 0.3298 |
71
- | 0.3164 | 18.0 | 169722 | 0.3316 |
72
- | 0.3172 | 19.0 | 179151 | 0.3315 |
73
- | 0.3179 | 20.0 | 188580 | 0.3318 |
74
 
75
 
76
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the NST Danish ASR Database dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3387
23
+ - Mae: 0.1486
24
+ - Mse: 0.0395
25
+ - Mcd: 16.3878
26
+ - Mae Rmcd: 0.1562
27
 
28
  ## Model description
29
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Mae | Mse | Mcd | Mae Rmcd |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:-------:|:--------:|
58
+ | 0.4202 | 1.0 | 2378 | 0.3851 | 0.1589 | 0.0446 | 17.5859 | 0.1674 |
59
+ | 0.3897 | 2.0 | 4756 | 0.3771 | 0.1578 | 0.0440 | 17.2975 | 0.1654 |
60
+ | 0.3749 | 3.0 | 7134 | 0.3636 | 0.1605 | 0.0450 | 17.3449 | 0.1670 |
61
+ | 0.359 | 4.0 | 9512 | 0.3632 | 0.1580 | 0.0443 | 17.2756 | 0.1654 |
62
+ | 0.3532 | 5.0 | 11890 | 0.3539 | 0.1592 | 0.0444 | 17.1294 | 0.1653 |
63
+ | 0.356 | 6.0 | 14268 | 0.3455 | 0.1536 | 0.0418 | 16.9892 | 0.1617 |
64
+ | 0.3437 | 7.0 | 16646 | 0.3426 | 0.1528 | 0.0416 | 16.8165 | 0.1605 |
65
+ | 0.3434 | 8.0 | 19024 | 0.3438 | 0.1534 | 0.0416 | 16.8859 | 0.1611 |
66
+ | 0.3391 | 9.0 | 21402 | 0.3487 | 0.1558 | 0.0429 | 16.7245 | 0.1615 |
67
+ | 0.3381 | 10.0 | 23780 | 0.3414 | 0.1516 | 0.0409 | 16.6136 | 0.1589 |
68
+ | 0.3455 | 11.0 | 26158 | 0.3395 | 0.1509 | 0.0406 | 16.6252 | 0.1586 |
69
+ | 0.3408 | 12.0 | 28536 | 0.3402 | 0.1504 | 0.0404 | 16.7043 | 0.1587 |
70
+ | 0.341 | 13.0 | 30914 | 0.3420 | 0.1527 | 0.0414 | 16.6290 | 0.1595 |
71
+ | 0.3279 | 14.0 | 33292 | 0.3388 | 0.1503 | 0.0404 | 16.5525 | 0.1579 |
72
+ | 0.328 | 15.0 | 35670 | 0.3389 | 0.1498 | 0.0401 | 16.4898 | 0.1574 |
73
+ | 0.3264 | 16.0 | 38048 | 0.3391 | 0.1497 | 0.0400 | 16.4882 | 0.1573 |
74
+ | 0.3318 | 17.0 | 40426 | 0.3383 | 0.1498 | 0.0402 | 16.5091 | 0.1575 |
75
+ | 0.3299 | 18.0 | 42804 | 0.3399 | 0.1492 | 0.0399 | 16.4604 | 0.1569 |
76
+ | 0.3304 | 19.0 | 45182 | 0.3399 | 0.1489 | 0.0396 | 16.4132 | 0.1565 |
77
+ | 0.3204 | 20.0 | 47560 | 0.3387 | 0.1486 | 0.0395 | 16.3878 | 0.1562 |
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dff4359a3c72168158595b8f34cbf6aa51f98f47264b71477a6115de94707c2f
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c6ec321502807c09c3c20ace355e731277993bcd68dc7a7fa1c545e5fe33e4
3
  size 577789320
runs/Feb15_13-20-07_CDT-DESKTOP-LINUX/events.out.tfevents.1707999610.CDT-DESKTOP-LINUX.28602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1969f5fb134c9e3e1ff6d50f10ef8009bb6da102ff620333c91554c3f942e4c9
3
+ size 20930
runs/Feb15_14-00-58_CDT-DESKTOP-LINUX/events.out.tfevents.1708002061.CDT-DESKTOP-LINUX.29532.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa57361707b6f66752b336bdac87e6b76daaf3a219c96450b39a200c1afd2a1
3
+ size 20928
runs/Feb15_14-12-26_CDT-DESKTOP-LINUX/events.out.tfevents.1708002746.CDT-DESKTOP-LINUX.30252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e386cd046565ad4d644a0d9a2f0010950f58a9d6b342e6968686f7fec3213d06
3
+ size 318135
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7826ab175be8e113f8950ea58524622eadd9e37fa5d3f1e7b3d7377d06b01a48
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52f7f9d69183ba12141be8a1a08e44e91ab923beaf934561eebeb356ad5712d
3
  size 4920