update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,23 +1,25 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model: microsoft/speecht5_tts
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
- voxpopuli
|
| 8 |
model-index:
|
| 9 |
-
- name:
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
#
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -36,36 +38,28 @@ More information needed
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
-
- learning_rate:
|
| 40 |
-
- train_batch_size:
|
| 41 |
- eval_batch_size: 4
|
| 42 |
- seed: 42
|
| 43 |
-
- gradient_accumulation_steps: 2
|
| 44 |
-
- total_train_batch_size: 32
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 500
|
| 48 |
-
- training_steps:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.5602 | 2.15 | 500 | 0.5003 |
|
| 59 |
-
| 0.5337 | 2.58 | 600 | 0.4931 |
|
| 60 |
-
| 0.5357 | 3.01 | 700 | 0.4881 |
|
| 61 |
-
| 0.5315 | 3.44 | 800 | 0.4841 |
|
| 62 |
-
| 0.5248 | 3.87 | 900 | 0.4828 |
|
| 63 |
-
| 0.5281 | 4.3 | 1000 | 0.4817 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
-
- Transformers 4.31.0
|
| 69 |
- Pytorch 2.0.1+cu118
|
| 70 |
-
- Datasets 2.
|
| 71 |
- Tokenizers 0.13.3
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- nl
|
| 4 |
license: mit
|
| 5 |
base_model: microsoft/speecht5_tts
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
+
- facebook/voxpopuli
|
| 10 |
model-index:
|
| 11 |
+
- name: speec T5 NL - Sumet
|
| 12 |
results: []
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
+
# speec T5 NL - Sumet
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Vox Populi NL dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: nan
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.003
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
- eval_batch_size: 4
|
| 44 |
- seed: 42
|
|
|
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- training_steps: 4000
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.0 | 0.54 | 1000 | nan |
|
| 55 |
+
| 0.0 | 1.09 | 2000 | nan |
|
| 56 |
+
| 0.0 | 1.63 | 3000 | nan |
|
| 57 |
+
| 0.0 | 2.18 | 4000 | nan |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
| 61 |
|
| 62 |
+
- Transformers 4.31.0
|
| 63 |
- Pytorch 2.0.1+cu118
|
| 64 |
+
- Datasets 2.14.0
|
| 65 |
- Tokenizers 0.13.3
|