End of training
Browse files- README.md +84 -0
- generation_config.json +9 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- sk
|
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: SpeechT5 TTS Slovak v3
|
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 |
+
# SpeechT5 TTS Slovak v3
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.4046
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 2
|
46 |
+
- total_train_batch_size: 64
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 500
|
50 |
+
- training_steps: 10000
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
57 |
+
| 0.5259 | 3.2258 | 500 | 0.4625 |
|
58 |
+
| 0.4823 | 6.4516 | 1000 | 0.4345 |
|
59 |
+
| 0.4702 | 9.6774 | 1500 | 0.4258 |
|
60 |
+
| 0.4502 | 12.9032 | 2000 | 0.4189 |
|
61 |
+
| 0.4579 | 16.1290 | 2500 | 0.4173 |
|
62 |
+
| 0.4418 | 19.3548 | 3000 | 0.4134 |
|
63 |
+
| 0.448 | 22.5806 | 3500 | 0.4117 |
|
64 |
+
| 0.4467 | 25.8065 | 4000 | 0.4094 |
|
65 |
+
| 0.4388 | 29.0323 | 4500 | 0.4084 |
|
66 |
+
| 0.4327 | 32.2581 | 5000 | 0.4071 |
|
67 |
+
| 0.4398 | 35.4839 | 5500 | 0.4069 |
|
68 |
+
| 0.4381 | 38.7097 | 6000 | 0.4065 |
|
69 |
+
| 0.4357 | 41.9355 | 6500 | 0.4053 |
|
70 |
+
| 0.4352 | 45.1613 | 7000 | 0.4059 |
|
71 |
+
| 0.4298 | 48.3871 | 7500 | 0.4050 |
|
72 |
+
| 0.4293 | 51.6129 | 8000 | 0.4043 |
|
73 |
+
| 0.4342 | 54.8387 | 8500 | 0.4050 |
|
74 |
+
| 0.4309 | 58.0645 | 9000 | 0.4045 |
|
75 |
+
| 0.4277 | 61.2903 | 9500 | 0.4047 |
|
76 |
+
| 0.4319 | 64.5161 | 10000 | 0.4046 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.42.0.dev0
|
82 |
+
- Pytorch 2.3.0+cu121
|
83 |
+
- Datasets 2.20.0
|
84 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"max_length": 1876,
|
7 |
+
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.42.0.dev0"
|
9 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577838472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36234a5d078888c6e7880bbb5957cfd3c8725505277b61f9d0d3826db4c12b46
|
3 |
size 577838472
|