Commit
•
b5edbde
1
Parent(s):
3758725
Model save
Browse files
README.md
CHANGED
|
@@ -1,26 +1,21 @@
|
|
| 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:
|
| 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 |
-
#
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -39,7 +34,7 @@ More information needed
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
-
- learning_rate:
|
| 43 |
- train_batch_size: 4
|
| 44 |
- eval_batch_size: 4
|
| 45 |
- seed: 42
|
|
@@ -53,126 +48,126 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 56 |
-
| No log | 0.53 | 250 |
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
-
| 0.
|
| 174 |
-
| 0.
|
| 175 |
-
| 0.
|
| 176 |
|
| 177 |
|
| 178 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model: microsoft/speecht5_tts
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
+
- name: speecht5_tts
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# speecht5_tts
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7806
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
- train_batch_size: 4
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| No log | 0.53 | 250 | 0.8506 |
|
| 52 |
+
| 1.0736 | 1.06 | 500 | 0.8219 |
|
| 53 |
+
| 1.0736 | 1.6 | 750 | 0.7713 |
|
| 54 |
+
| 0.8607 | 2.13 | 1000 | 0.7947 |
|
| 55 |
+
| 0.8607 | 2.66 | 1250 | 0.7537 |
|
| 56 |
+
| 0.802 | 3.19 | 1500 | 0.7304 |
|
| 57 |
+
| 0.802 | 3.72 | 1750 | 0.7409 |
|
| 58 |
+
| 0.7627 | 4.26 | 2000 | 0.7282 |
|
| 59 |
+
| 0.7627 | 4.79 | 2250 | 0.7224 |
|
| 60 |
+
| 0.7442 | 5.32 | 2500 | 0.7132 |
|
| 61 |
+
| 0.7442 | 5.85 | 2750 | 0.7718 |
|
| 62 |
+
| 0.736 | 6.38 | 3000 | 0.7362 |
|
| 63 |
+
| 0.736 | 6.91 | 3250 | 0.7283 |
|
| 64 |
+
| 0.7234 | 7.45 | 3500 | 0.7377 |
|
| 65 |
+
| 0.7234 | 7.98 | 3750 | 0.7226 |
|
| 66 |
+
| 0.6968 | 8.51 | 4000 | 0.7285 |
|
| 67 |
+
| 0.6968 | 9.04 | 4250 | 0.7395 |
|
| 68 |
+
| 0.692 | 9.57 | 4500 | 0.7306 |
|
| 69 |
+
| 0.692 | 10.11 | 4750 | 0.7221 |
|
| 70 |
+
| 0.6807 | 10.64 | 5000 | 0.7349 |
|
| 71 |
+
| 0.6807 | 11.17 | 5250 | 0.7310 |
|
| 72 |
+
| 0.6702 | 11.7 | 5500 | 0.7391 |
|
| 73 |
+
| 0.6702 | 12.23 | 5750 | 0.7299 |
|
| 74 |
+
| 0.6559 | 12.77 | 6000 | 0.7277 |
|
| 75 |
+
| 0.6559 | 13.3 | 6250 | 0.7453 |
|
| 76 |
+
| 0.6511 | 13.83 | 6500 | 0.7303 |
|
| 77 |
+
| 0.6511 | 14.36 | 6750 | 0.7451 |
|
| 78 |
+
| 0.6335 | 14.89 | 7000 | 0.7209 |
|
| 79 |
+
| 0.6335 | 15.43 | 7250 | 0.7421 |
|
| 80 |
+
| 0.6282 | 15.96 | 7500 | 0.7277 |
|
| 81 |
+
| 0.6282 | 16.49 | 7750 | 0.7426 |
|
| 82 |
+
| 0.6286 | 17.02 | 8000 | 0.7724 |
|
| 83 |
+
| 0.6286 | 17.55 | 8250 | 0.7310 |
|
| 84 |
+
| 0.6164 | 18.09 | 8500 | 0.7414 |
|
| 85 |
+
| 0.6164 | 18.62 | 8750 | 0.7411 |
|
| 86 |
+
| 0.6029 | 19.15 | 9000 | 0.7466 |
|
| 87 |
+
| 0.6029 | 19.68 | 9250 | 0.7267 |
|
| 88 |
+
| 0.5986 | 20.21 | 9500 | 0.7593 |
|
| 89 |
+
| 0.5986 | 20.74 | 9750 | 0.7544 |
|
| 90 |
+
| 0.595 | 21.28 | 10000 | 0.7441 |
|
| 91 |
+
| 0.595 | 21.81 | 10250 | 0.7422 |
|
| 92 |
+
| 0.5905 | 22.34 | 10500 | 0.7399 |
|
| 93 |
+
| 0.5905 | 22.87 | 10750 | 0.7494 |
|
| 94 |
+
| 0.5792 | 23.4 | 11000 | 0.7311 |
|
| 95 |
+
| 0.5792 | 23.94 | 11250 | 0.7479 |
|
| 96 |
+
| 0.5774 | 24.47 | 11500 | 0.7615 |
|
| 97 |
+
| 0.5774 | 25.0 | 11750 | 0.7578 |
|
| 98 |
+
| 0.5684 | 25.53 | 12000 | 0.7603 |
|
| 99 |
+
| 0.5684 | 26.06 | 12250 | 0.7300 |
|
| 100 |
+
| 0.5621 | 26.6 | 12500 | 0.7385 |
|
| 101 |
+
| 0.5621 | 27.13 | 12750 | 0.7447 |
|
| 102 |
+
| 0.5666 | 27.66 | 13000 | 0.7400 |
|
| 103 |
+
| 0.5666 | 28.19 | 13250 | 0.7518 |
|
| 104 |
+
| 0.5525 | 28.72 | 13500 | 0.7462 |
|
| 105 |
+
| 0.5525 | 29.26 | 13750 | 0.7351 |
|
| 106 |
+
| 0.5471 | 29.79 | 14000 | 0.7673 |
|
| 107 |
+
| 0.5471 | 30.32 | 14250 | 0.7325 |
|
| 108 |
+
| 0.5449 | 30.85 | 14500 | 0.7455 |
|
| 109 |
+
| 0.5449 | 31.38 | 14750 | 0.7473 |
|
| 110 |
+
| 0.5349 | 31.91 | 15000 | 0.7549 |
|
| 111 |
+
| 0.5349 | 32.45 | 15250 | 0.7513 |
|
| 112 |
+
| 0.5345 | 32.98 | 15500 | 0.7472 |
|
| 113 |
+
| 0.5345 | 33.51 | 15750 | 0.7542 |
|
| 114 |
+
| 0.5285 | 34.04 | 16000 | 0.7513 |
|
| 115 |
+
| 0.5285 | 34.57 | 16250 | 0.7466 |
|
| 116 |
+
| 0.522 | 35.11 | 16500 | 0.7627 |
|
| 117 |
+
| 0.522 | 35.64 | 16750 | 0.7609 |
|
| 118 |
+
| 0.5209 | 36.17 | 17000 | 0.7616 |
|
| 119 |
+
| 0.5209 | 36.7 | 17250 | 0.7612 |
|
| 120 |
+
| 0.5151 | 37.23 | 17500 | 0.7601 |
|
| 121 |
+
| 0.5151 | 37.77 | 17750 | 0.7590 |
|
| 122 |
+
| 0.5088 | 38.3 | 18000 | 0.7568 |
|
| 123 |
+
| 0.5088 | 38.83 | 18250 | 0.7551 |
|
| 124 |
+
| 0.5105 | 39.36 | 18500 | 0.7688 |
|
| 125 |
+
| 0.5105 | 39.89 | 18750 | 0.7631 |
|
| 126 |
+
| 0.5046 | 40.43 | 19000 | 0.7654 |
|
| 127 |
+
| 0.5046 | 40.96 | 19250 | 0.7749 |
|
| 128 |
+
| 0.5029 | 41.49 | 19500 | 0.7617 |
|
| 129 |
+
| 0.5029 | 42.02 | 19750 | 0.7735 |
|
| 130 |
+
| 0.4969 | 42.55 | 20000 | 0.7763 |
|
| 131 |
+
| 0.4969 | 43.09 | 20250 | 0.7484 |
|
| 132 |
+
| 0.497 | 43.62 | 20500 | 0.7606 |
|
| 133 |
+
| 0.497 | 44.15 | 20750 | 0.7726 |
|
| 134 |
+
| 0.4889 | 44.68 | 21000 | 0.7564 |
|
| 135 |
+
| 0.4889 | 45.21 | 21250 | 0.7694 |
|
| 136 |
+
| 0.4842 | 45.74 | 21500 | 0.7639 |
|
| 137 |
+
| 0.4842 | 46.28 | 21750 | 0.7784 |
|
| 138 |
+
| 0.4829 | 46.81 | 22000 | 0.7817 |
|
| 139 |
+
| 0.4829 | 47.34 | 22250 | 0.7727 |
|
| 140 |
+
| 0.4772 | 47.87 | 22500 | 0.7661 |
|
| 141 |
+
| 0.4772 | 48.4 | 22750 | 0.7630 |
|
| 142 |
+
| 0.477 | 48.94 | 23000 | 0.7640 |
|
| 143 |
+
| 0.477 | 49.47 | 23250 | 0.7730 |
|
| 144 |
+
| 0.4766 | 50.0 | 23500 | 0.7708 |
|
| 145 |
+
| 0.4766 | 50.53 | 23750 | 0.7716 |
|
| 146 |
+
| 0.4717 | 51.06 | 24000 | 0.7670 |
|
| 147 |
+
| 0.4717 | 51.6 | 24250 | 0.7671 |
|
| 148 |
+
| 0.4686 | 52.13 | 24500 | 0.7711 |
|
| 149 |
+
| 0.4686 | 52.66 | 24750 | 0.7704 |
|
| 150 |
+
| 0.4685 | 53.19 | 25000 | 0.7775 |
|
| 151 |
+
| 0.4685 | 53.72 | 25250 | 0.7690 |
|
| 152 |
+
| 0.4635 | 54.26 | 25500 | 0.7839 |
|
| 153 |
+
| 0.4635 | 54.79 | 25750 | 0.7746 |
|
| 154 |
+
| 0.4617 | 55.32 | 26000 | 0.7738 |
|
| 155 |
+
| 0.4617 | 55.85 | 26250 | 0.7753 |
|
| 156 |
+
| 0.4549 | 56.38 | 26500 | 0.7830 |
|
| 157 |
+
| 0.4549 | 56.91 | 26750 | 0.7777 |
|
| 158 |
+
| 0.4564 | 57.45 | 27000 | 0.7758 |
|
| 159 |
+
| 0.4564 | 57.98 | 27250 | 0.7728 |
|
| 160 |
+
| 0.4546 | 58.51 | 27500 | 0.7772 |
|
| 161 |
+
| 0.4546 | 59.04 | 27750 | 0.7795 |
|
| 162 |
+
| 0.4511 | 59.57 | 28000 | 0.7754 |
|
| 163 |
+
| 0.4511 | 60.11 | 28250 | 0.7867 |
|
| 164 |
+
| 0.4467 | 60.64 | 28500 | 0.7838 |
|
| 165 |
+
| 0.4467 | 61.17 | 28750 | 0.7858 |
|
| 166 |
+
| 0.4512 | 61.7 | 29000 | 0.7758 |
|
| 167 |
+
| 0.4512 | 62.23 | 29250 | 0.7819 |
|
| 168 |
+
| 0.4497 | 62.77 | 29500 | 0.7871 |
|
| 169 |
+
| 0.4497 | 63.3 | 29750 | 0.7817 |
|
| 170 |
+
| 0.4463 | 63.83 | 30000 | 0.7806 |
|
| 171 |
|
| 172 |
|
| 173 |
### Framework versions
|
runs/Dec10_15-46-46_Threadripper/events.out.tfevents.1702241206.Threadripper
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:714c7ec0d4433460160db6dd9f8c8b6a9398c1b32192230ca0750eef1239edf2
|
| 3 |
+
size 48488
|