update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- voxpopuli
|
| 7 |
+
model-index:
|
| 8 |
+
- name: speecht5_finetuned_voxpopuli_it
|
| 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_voxpopuli_it
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4968
|
| 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: 0.0005
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 25
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.6707 | 1.0 | 108 | 0.5946 |
|
| 54 |
+
| 0.6625 | 2.0 | 217 | 0.6029 |
|
| 55 |
+
| 0.708 | 3.0 | 325 | 0.6118 |
|
| 56 |
+
| 0.6588 | 4.0 | 434 | 0.7109 |
|
| 57 |
+
| 0.6614 | 5.0 | 542 | 0.5799 |
|
| 58 |
+
| 0.6375 | 6.0 | 651 | 0.5714 |
|
| 59 |
+
| 0.619 | 7.0 | 759 | 0.5699 |
|
| 60 |
+
| 0.5806 | 8.0 | 868 | 0.5538 |
|
| 61 |
+
| 0.6024 | 9.0 | 976 | 0.5856 |
|
| 62 |
+
| 0.5728 | 10.0 | 1085 | 0.5446 |
|
| 63 |
+
| 0.5624 | 11.0 | 1193 | 0.5508 |
|
| 64 |
+
| 0.5711 | 12.0 | 1302 | 0.5376 |
|
| 65 |
+
| 0.5438 | 13.0 | 1410 | 0.5300 |
|
| 66 |
+
| 0.5308 | 14.0 | 1519 | 0.5206 |
|
| 67 |
+
| 0.5536 | 15.0 | 1627 | 0.5359 |
|
| 68 |
+
| 0.5285 | 16.0 | 1736 | 0.5264 |
|
| 69 |
+
| 0.525 | 17.0 | 1844 | 0.5108 |
|
| 70 |
+
| 0.4961 | 18.0 | 1953 | 0.5116 |
|
| 71 |
+
| 0.5111 | 19.0 | 2061 | 0.5042 |
|
| 72 |
+
| 0.4869 | 20.0 | 2170 | 0.5050 |
|
| 73 |
+
| 0.4864 | 21.0 | 2278 | 0.4994 |
|
| 74 |
+
| 0.4794 | 22.0 | 2387 | 0.5039 |
|
| 75 |
+
| 0.4787 | 23.0 | 2495 | 0.4975 |
|
| 76 |
+
| 0.4692 | 24.0 | 2604 | 0.4961 |
|
| 77 |
+
| 0.4656 | 24.88 | 2700 | 0.4968 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.30.2
|
| 83 |
+
- Pytorch 2.0.0
|
| 84 |
+
- Datasets 2.1.0
|
| 85 |
+
- Tokenizers 0.13.3
|