End of training
Browse files- README.md +100 -0
- generation_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: speecht5_improved_data_less_steps
|
| 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_improved_data_less_steps
|
| 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: 0.6468
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 2
|
| 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
|
| 45 |
+
- lr_scheduler_warmup_steps: 250
|
| 46 |
+
- training_steps: 1000
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 1.4475 | 0.1533 | 25 | 1.1070 |
|
| 54 |
+
| 1.3754 | 0.3065 | 50 | 1.0239 |
|
| 55 |
+
| 1.2957 | 0.4598 | 75 | 0.9667 |
|
| 56 |
+
| 1.1821 | 0.6130 | 100 | 0.9231 |
|
| 57 |
+
| 1.1414 | 0.7663 | 125 | 0.8946 |
|
| 58 |
+
| 1.0555 | 0.9195 | 150 | 0.8335 |
|
| 59 |
+
| 0.9565 | 1.0728 | 175 | 0.7764 |
|
| 60 |
+
| 0.9189 | 1.2261 | 200 | 0.7485 |
|
| 61 |
+
| 0.8751 | 1.3793 | 225 | 0.7332 |
|
| 62 |
+
| 0.8533 | 1.5326 | 250 | 0.7197 |
|
| 63 |
+
| 0.8219 | 1.6858 | 275 | 0.7133 |
|
| 64 |
+
| 0.8171 | 1.8391 | 300 | 0.7009 |
|
| 65 |
+
| 0.8088 | 1.9923 | 325 | 0.6926 |
|
| 66 |
+
| 0.785 | 2.1456 | 350 | 0.6877 |
|
| 67 |
+
| 0.7989 | 2.2989 | 375 | 0.6824 |
|
| 68 |
+
| 0.7755 | 2.4521 | 400 | 0.6784 |
|
| 69 |
+
| 0.7914 | 2.6054 | 425 | 0.6738 |
|
| 70 |
+
| 0.7696 | 2.7586 | 450 | 0.6694 |
|
| 71 |
+
| 0.7741 | 2.9119 | 475 | 0.6680 |
|
| 72 |
+
| 0.7613 | 3.0651 | 500 | 0.6659 |
|
| 73 |
+
| 0.7733 | 3.2184 | 525 | 0.6654 |
|
| 74 |
+
| 0.7605 | 3.3716 | 550 | 0.6623 |
|
| 75 |
+
| 0.7538 | 3.5249 | 575 | 0.6606 |
|
| 76 |
+
| 0.7626 | 3.6782 | 600 | 0.6596 |
|
| 77 |
+
| 0.7573 | 3.8314 | 625 | 0.6577 |
|
| 78 |
+
| 0.7469 | 3.9847 | 650 | 0.6556 |
|
| 79 |
+
| 0.7524 | 4.1379 | 675 | 0.6537 |
|
| 80 |
+
| 0.7342 | 4.2912 | 700 | 0.6491 |
|
| 81 |
+
| 0.7305 | 4.4444 | 725 | 0.6511 |
|
| 82 |
+
| 0.7433 | 4.5977 | 750 | 0.6486 |
|
| 83 |
+
| 0.7438 | 4.7510 | 775 | 0.6487 |
|
| 84 |
+
| 0.7505 | 4.9042 | 800 | 0.6481 |
|
| 85 |
+
| 0.7354 | 5.0575 | 825 | 0.6450 |
|
| 86 |
+
| 0.7354 | 5.2107 | 850 | 0.6439 |
|
| 87 |
+
| 0.7333 | 5.3640 | 875 | 0.6462 |
|
| 88 |
+
| 0.7246 | 5.5172 | 900 | 0.6444 |
|
| 89 |
+
| 0.7289 | 5.6705 | 925 | 0.6417 |
|
| 90 |
+
| 0.7436 | 5.8238 | 950 | 0.6474 |
|
| 91 |
+
| 0.741 | 5.9770 | 975 | 0.6428 |
|
| 92 |
+
| 0.7443 | 6.1303 | 1000 | 0.6468 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.41.2
|
| 98 |
+
- Pytorch 2.1.2
|
| 99 |
+
- Datasets 2.17.0
|
| 100 |
+
- Tokenizers 0.19.1
|
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": "4.41.2"
|
| 9 |
+
}
|