Hugging Face's logo

mikhail-panzo
/
zlm_b64_le4_s8000

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files Metrics Community
mikhail-panzo commited on
Commit
5eedeb1
·
verified ·
1 Parent(s): 947c4bd

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -21
  2. model.safetensors +1 -1
  3. runs/May06_05-29-07_20bf46497c89/events.out.tfevents.1714973361.20bf46497c89.2091.1 +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3180
19
 
20
  ## Model description
21
 
@@ -35,10 +35,10 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0001
38
- - train_batch_size: 32
39
  - eval_batch_size: 8
40
  - seed: 42
41
- - gradient_accumulation_steps: 2
42
  - total_train_batch_size: 64
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
@@ -48,24 +48,24 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:------:|:----:|:---------------:|
53
- | 0.4057 | 0.4188 | 500 | 0.3683 |
54
- | 0.416 | 0.8375 | 1000 | 0.3688 |
55
- | 0.4037 | 1.2563 | 1500 | 0.3661 |
56
- | 0.4098 | 1.6750 | 2000 | 0.3715 |
57
- | 0.4019 | 2.0938 | 2500 | 0.3573 |
58
- | 0.3899 | 2.5126 | 3000 | 0.3552 |
59
- | 0.3798 | 2.9313 | 3500 | 0.3438 |
60
- | 0.3737 | 3.3501 | 4000 | 0.3414 |
61
- | 0.3687 | 3.7688 | 4500 | 0.3459 |
62
- | 0.3597 | 4.1876 | 5000 | 0.3316 |
63
- | 0.3626 | 4.6064 | 5500 | 0.3270 |
64
- | 0.3583 | 5.0251 | 6000 | 0.3233 |
65
- | 0.3545 | 5.4439 | 6500 | 0.3212 |
66
- | 0.3473 | 5.8626 | 7000 | 0.3196 |
67
- | 0.3453 | 6.2814 | 7500 | 0.3189 |
68
- | 0.3453 | 6.7002 | 8000 | 0.3180 |
69
 
70
 
71
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.3177
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0001
38
+ - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 8
42
  - total_train_batch_size: 64
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-------:|:----:|:---------------:|
53
+ | 0.5277 | 0.4188 | 500 | 0.4806 |
54
+ | 0.4582 | 0.8377 | 1000 | 0.4116 |
55
+ | 0.4312 | 1.2565 | 1500 | 0.3951 |
56
+ | 0.4122 | 1.6754 | 2000 | 0.3768 |
57
+ | 0.4002 | 2.0942 | 2500 | 0.3599 |
58
+ | 0.3905 | 2.5131 | 3000 | 0.3521 |
59
+ | 0.3806 | 2.9319 | 3500 | 0.3445 |
60
+ | 0.37 | 3.3508 | 4000 | 0.3474 |
61
+ | 0.3736 | 3.7696 | 4500 | 0.3362 |
62
+ | 0.3608 | 8.3872 | 5000 | 0.3342 |
63
+ | 0.3602 | 9.2249 | 5500 | 0.3258 |
64
+ | 0.3561 | 10.0626 | 6000 | 0.3230 |
65
+ | 0.3505 | 10.9003 | 6500 | 0.3199 |
66
+ | 0.3473 | 11.7380 | 7000 | 0.3193 |
67
+ | 0.3523 | 12.5757 | 7500 | 0.3177 |
68
+ | 0.3462 | 13.4134 | 8000 | 0.3177 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05e55c22b762d52b9d362d21d1a3deb06e5eafa86fcf99357fd3ac26f86f57db
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9496de2c009f4d705b17f625395263edf16c42258287bba1b184b1131d78bcc3
3
  size 577789320
runs/May06_05-29-07_20bf46497c89/events.out.tfevents.1714973361.20bf46497c89.2091.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f891f2ff0a33b420588f9a1baa74b2db464e60aa5599842368f46e245b74268
3
- size 23151
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d744fb2b60e54f15bc1ddc02e52668b0e1a7c0d8587da5d0e0d7d6ea655c4c8
3
+ size 23505