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_pl
|
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_pl
|
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: 0.4550
|
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: 1e-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: 2000
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.6954 | 0.5 | 100 | 0.6110 |
|
55 |
+
| 0.644 | 1.01 | 200 | 0.5731 |
|
56 |
+
| 0.602 | 1.51 | 300 | 0.5330 |
|
57 |
+
| 0.5524 | 2.01 | 400 | 0.4982 |
|
58 |
+
| 0.5412 | 2.51 | 500 | 0.4870 |
|
59 |
+
| 0.5256 | 3.02 | 600 | 0.4775 |
|
60 |
+
| 0.5141 | 3.52 | 700 | 0.4728 |
|
61 |
+
| 0.5125 | 4.02 | 800 | 0.4688 |
|
62 |
+
| 0.5106 | 4.52 | 900 | 0.4657 |
|
63 |
+
| 0.5037 | 5.03 | 1000 | 0.4627 |
|
64 |
+
| 0.5048 | 5.53 | 1100 | 0.4622 |
|
65 |
+
| 0.4983 | 6.03 | 1200 | 0.4583 |
|
66 |
+
| 0.4981 | 6.53 | 1300 | 0.4580 |
|
67 |
+
| 0.4942 | 7.04 | 1400 | 0.4580 |
|
68 |
+
| 0.4945 | 7.54 | 1500 | 0.4578 |
|
69 |
+
| 0.4922 | 8.04 | 1600 | 0.4568 |
|
70 |
+
| 0.4893 | 8.54 | 1700 | 0.4562 |
|
71 |
+
| 0.4948 | 9.05 | 1800 | 0.4552 |
|
72 |
+
| 0.4892 | 9.55 | 1900 | 0.4547 |
|
73 |
+
| 0.4933 | 10.05 | 2000 | 0.4550 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.31.0
|
79 |
+
- Pytorch 2.0.1+cu117
|
80 |
+
- Datasets 2.14.0
|
81 |
+
- Tokenizers 0.13.3
|