update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- voxpopuli
|
| 7 |
+
model-index:
|
| 8 |
+
- name: speecht5_finetuned_voxpopuli_nl
|
| 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_nl
|
| 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: 0.4816
|
| 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: 1e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 250
|
| 47 |
+
- training_steps: 1000
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.8188 | 0.85 | 50 | 0.7075 |
|
| 54 |
+
| 0.7124 | 1.71 | 100 | 0.6201 |
|
| 55 |
+
| 0.6763 | 2.56 | 150 | 0.5924 |
|
| 56 |
+
| 0.6367 | 3.42 | 200 | 0.5586 |
|
| 57 |
+
| 0.576 | 4.27 | 250 | 0.5216 |
|
| 58 |
+
| 0.5591 | 5.13 | 300 | 0.5097 |
|
| 59 |
+
| 0.5457 | 5.98 | 350 | 0.5027 |
|
| 60 |
+
| 0.5447 | 6.84 | 400 | 0.4999 |
|
| 61 |
+
| 0.5413 | 7.69 | 450 | 0.4933 |
|
| 62 |
+
| 0.5288 | 8.55 | 500 | 0.4913 |
|
| 63 |
+
| 0.5231 | 9.4 | 550 | 0.4881 |
|
| 64 |
+
| 0.5276 | 10.26 | 600 | 0.4874 |
|
| 65 |
+
| 0.52 | 11.11 | 650 | 0.4848 |
|
| 66 |
+
| 0.5238 | 11.97 | 700 | 0.4863 |
|
| 67 |
+
| 0.5163 | 12.82 | 750 | 0.4848 |
|
| 68 |
+
| 0.5191 | 13.68 | 800 | 0.4838 |
|
| 69 |
+
| 0.5163 | 14.53 | 850 | 0.4828 |
|
| 70 |
+
| 0.5126 | 15.38 | 900 | 0.4824 |
|
| 71 |
+
| 0.5155 | 16.24 | 950 | 0.4836 |
|
| 72 |
+
| 0.5193 | 17.09 | 1000 | 0.4816 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.31.0.dev0
|
| 78 |
+
- Pytorch 2.0.1+cu118
|
| 79 |
+
- Datasets 2.14.4
|
| 80 |
+
- Tokenizers 0.13.3
|