End of training
Browse files- README.md +80 -0
- generation_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: maghrane/speecht5_finetuned_marar1000
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: speecht5_finetuned_marar2000
|
| 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 |
+
# speecht5_finetuned_marar2000
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [maghrane/speecht5_finetuned_marar1000](https://huggingface.co/maghrane/speecht5_finetuned_marar1000) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4801
|
| 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: 0.0001
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 8
|
| 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: 100
|
| 47 |
+
- training_steps: 2000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 54 |
+
| 0.528 | 0.7976 | 100 | 0.5440 |
|
| 55 |
+
| 0.5453 | 1.5952 | 200 | 0.5655 |
|
| 56 |
+
| 0.5395 | 2.3928 | 300 | 0.5418 |
|
| 57 |
+
| 0.5421 | 3.1904 | 400 | 0.5570 |
|
| 58 |
+
| 0.5384 | 3.9880 | 500 | 0.5324 |
|
| 59 |
+
| 0.5447 | 4.7856 | 600 | 0.5454 |
|
| 60 |
+
| 0.5343 | 5.5833 | 700 | 0.5220 |
|
| 61 |
+
| 0.5165 | 6.3809 | 800 | 0.5269 |
|
| 62 |
+
| 0.5171 | 7.1785 | 900 | 0.5223 |
|
| 63 |
+
| 0.507 | 7.9761 | 1000 | 0.5227 |
|
| 64 |
+
| 0.5021 | 8.7737 | 1100 | 0.5052 |
|
| 65 |
+
| 0.4982 | 9.5713 | 1200 | 0.5081 |
|
| 66 |
+
| 0.488 | 10.3689 | 1300 | 0.5026 |
|
| 67 |
+
| 0.4787 | 11.1665 | 1400 | 0.4902 |
|
| 68 |
+
| 0.4849 | 11.9641 | 1500 | 0.4936 |
|
| 69 |
+
| 0.4778 | 12.7617 | 1600 | 0.4934 |
|
| 70 |
+
| 0.4646 | 13.5593 | 1700 | 0.4858 |
|
| 71 |
+
| 0.4615 | 14.3569 | 1800 | 0.4894 |
|
| 72 |
+
| 0.4716 | 15.1545 | 1900 | 0.4832 |
|
| 73 |
+
| 0.4607 | 15.9521 | 2000 | 0.4801 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.46.2
|
| 79 |
+
- Pytorch 2.5.1+cu121
|
| 80 |
+
- Tokenizers 0.20.3
|
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": "4.46.2"
|
| 9 |
+
}
|