Commit
•
70b821e
1
Parent(s):
7dd7c6e
update model card README.md
Browse files
README.md
CHANGED
@@ -1,23 +1,24 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
-
- voxpopuli
|
7 |
model-index:
|
8 |
-
- name:
|
9 |
results: []
|
10 |
-
pipeline_tag: text-to-speech
|
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: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,7 +37,7 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
- train_batch_size: 8
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
@@ -51,26 +52,26 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:-----:|:---------------:|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
|
75 |
|
76 |
### Framework versions
|
@@ -78,4 +79,4 @@ The following hyperparameters were used during training:
|
|
78 |
- Transformers 4.30.0.dev0
|
79 |
- Pytorch 2.0.1+cu117
|
80 |
- Datasets 2.13.1
|
81 |
-
- Tokenizers 0.13.3
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- es
|
4 |
license: mit
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
+
- facebook/voxpopuli
|
9 |
model-index:
|
10 |
+
- name: SpeechT5-spanish
|
11 |
results: []
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# SpeechT5-spanish
|
18 |
|
19 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VOXPOPULI dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4355
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
- train_batch_size: 8
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:-----:|:---------------:|
|
55 |
+
| 0.484 | 1.0 | 1074 | 0.4623 |
|
56 |
+
| 0.4724 | 2.0 | 2148 | 0.4542 |
|
57 |
+
| 0.4646 | 3.0 | 3222 | 0.4474 |
|
58 |
+
| 0.463 | 4.0 | 4296 | 0.4451 |
|
59 |
+
| 0.4538 | 5.0 | 5370 | 0.4425 |
|
60 |
+
| 0.4509 | 6.0 | 6444 | 0.4408 |
|
61 |
+
| 0.4548 | 7.0 | 7518 | 0.4412 |
|
62 |
+
| 0.4465 | 8.0 | 8592 | 0.4389 |
|
63 |
+
| 0.4509 | 9.0 | 9666 | 0.4387 |
|
64 |
+
| 0.4424 | 10.0 | 10740 | 0.4369 |
|
65 |
+
| 0.4415 | 11.0 | 11814 | 0.4367 |
|
66 |
+
| 0.4386 | 12.0 | 12888 | 0.4366 |
|
67 |
+
| 0.4383 | 13.0 | 13962 | 0.4357 |
|
68 |
+
| 0.4396 | 14.0 | 15036 | 0.4348 |
|
69 |
+
| 0.4432 | 15.0 | 16110 | 0.4358 |
|
70 |
+
| 0.4378 | 16.0 | 17184 | 0.4356 |
|
71 |
+
| 0.4321 | 17.0 | 18258 | 0.4353 |
|
72 |
+
| 0.4381 | 18.0 | 19332 | 0.4353 |
|
73 |
+
| 0.4325 | 19.0 | 20406 | 0.4347 |
|
74 |
+
| 0.4336 | 20.0 | 21480 | 0.4355 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
79 |
- Transformers 4.30.0.dev0
|
80 |
- Pytorch 2.0.1+cu117
|
81 |
- Datasets 2.13.1
|
82 |
+
- Tokenizers 0.13.3
|