update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: speecht5_finetuned_voxpopuli_fr
|
| 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 |
+
# speecht5_finetuned_voxpopuli_fr
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4697
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 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: 1000
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.765 | 0.23 | 50 | 0.6575 |
|
| 55 |
+
| 0.687 | 0.47 | 100 | 0.6106 |
|
| 56 |
+
| 0.6423 | 0.7 | 150 | 0.5548 |
|
| 57 |
+
| 0.5792 | 0.94 | 200 | 0.5300 |
|
| 58 |
+
| 0.5658 | 1.17 | 250 | 0.5186 |
|
| 59 |
+
| 0.5558 | 1.41 | 300 | 0.5078 |
|
| 60 |
+
| 0.5484 | 1.64 | 350 | 0.5029 |
|
| 61 |
+
| 0.5427 | 1.87 | 400 | 0.4981 |
|
| 62 |
+
| 0.5349 | 2.11 | 450 | 0.4921 |
|
| 63 |
+
| 0.524 | 2.34 | 500 | 0.4906 |
|
| 64 |
+
| 0.5243 | 2.58 | 550 | 0.4857 |
|
| 65 |
+
| 0.5238 | 2.81 | 600 | 0.4835 |
|
| 66 |
+
| 0.5104 | 3.05 | 650 | 0.4796 |
|
| 67 |
+
| 0.516 | 3.28 | 700 | 0.4769 |
|
| 68 |
+
| 0.5084 | 3.51 | 750 | 0.4763 |
|
| 69 |
+
| 0.5029 | 3.75 | 800 | 0.4749 |
|
| 70 |
+
| 0.5015 | 3.98 | 850 | 0.4725 |
|
| 71 |
+
| 0.5045 | 4.22 | 900 | 0.4716 |
|
| 72 |
+
| 0.503 | 4.45 | 950 | 0.4706 |
|
| 73 |
+
| 0.5013 | 4.69 | 1000 | 0.4697 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.31.0
|
| 79 |
+
- Pytorch 2.0.1+cu118
|
| 80 |
+
- Datasets 2.14.2
|
| 81 |
+
- Tokenizers 0.13.3
|