End of training
Browse files- README.md +101 -0
- generation_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/speecht5_tts
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: vc
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# vc
|
| 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: 0.5712
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 64
|
| 44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- training_steps: 2000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 54 |
+
| 0.9951 | 2.0851 | 50 | 0.9152 |
|
| 55 |
+
| 0.9256 | 4.1702 | 100 | 0.8480 |
|
| 56 |
+
| 0.9001 | 6.2553 | 150 | 0.8114 |
|
| 57 |
+
| 0.8567 | 8.3404 | 200 | 0.7857 |
|
| 58 |
+
| 0.8139 | 10.4255 | 250 | 0.7477 |
|
| 59 |
+
| 0.7437 | 12.5106 | 300 | 0.6724 |
|
| 60 |
+
| 0.6937 | 14.5957 | 350 | 0.6352 |
|
| 61 |
+
| 0.6686 | 16.6809 | 400 | 0.6194 |
|
| 62 |
+
| 0.6487 | 18.7660 | 450 | 0.6070 |
|
| 63 |
+
| 0.6411 | 20.8511 | 500 | 0.6009 |
|
| 64 |
+
| 0.643 | 22.9362 | 550 | 0.5970 |
|
| 65 |
+
| 0.6158 | 25.0 | 600 | 0.5893 |
|
| 66 |
+
| 0.632 | 27.0851 | 650 | 0.5871 |
|
| 67 |
+
| 0.6152 | 29.1702 | 700 | 0.5855 |
|
| 68 |
+
| 0.6066 | 31.2553 | 750 | 0.5833 |
|
| 69 |
+
| 0.615 | 33.3404 | 800 | 0.5817 |
|
| 70 |
+
| 0.6011 | 35.4255 | 850 | 0.5812 |
|
| 71 |
+
| 0.598 | 37.5106 | 900 | 0.5788 |
|
| 72 |
+
| 0.6023 | 39.5957 | 950 | 0.5764 |
|
| 73 |
+
| 0.6031 | 41.6809 | 1000 | 0.5775 |
|
| 74 |
+
| 0.5976 | 43.7660 | 1050 | 0.5764 |
|
| 75 |
+
| 0.597 | 45.8511 | 1100 | 0.5772 |
|
| 76 |
+
| 0.5923 | 47.9362 | 1150 | 0.5727 |
|
| 77 |
+
| 0.5793 | 50.0 | 1200 | 0.5746 |
|
| 78 |
+
| 0.5879 | 52.0851 | 1250 | 0.5757 |
|
| 79 |
+
| 0.5908 | 54.1702 | 1300 | 0.5727 |
|
| 80 |
+
| 0.5838 | 56.2553 | 1350 | 0.5745 |
|
| 81 |
+
| 0.5852 | 58.3404 | 1400 | 0.5709 |
|
| 82 |
+
| 0.5869 | 60.4255 | 1450 | 0.5753 |
|
| 83 |
+
| 0.585 | 62.5106 | 1500 | 0.5720 |
|
| 84 |
+
| 0.5875 | 64.5957 | 1550 | 0.5715 |
|
| 85 |
+
| 0.5807 | 66.6809 | 1600 | 0.5729 |
|
| 86 |
+
| 0.5886 | 68.7660 | 1650 | 0.5730 |
|
| 87 |
+
| 0.5831 | 70.8511 | 1700 | 0.5753 |
|
| 88 |
+
| 0.5812 | 72.9362 | 1750 | 0.5711 |
|
| 89 |
+
| 0.5736 | 75.0 | 1800 | 0.5768 |
|
| 90 |
+
| 0.5761 | 77.0851 | 1850 | 0.5735 |
|
| 91 |
+
| 0.5767 | 79.1702 | 1900 | 0.5759 |
|
| 92 |
+
| 0.5777 | 81.2553 | 1950 | 0.5720 |
|
| 93 |
+
| 0.5759 | 83.3404 | 2000 | 0.5712 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.47.0
|
| 99 |
+
- Pytorch 2.5.1+cu121
|
| 100 |
+
- Datasets 3.3.1
|
| 101 |
+
- Tokenizers 0.21.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"max_length": 1876,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.47.0"
|
| 9 |
+
}
|