End of training
Browse files- README.md +75 -0
- generation_config.json +9 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: mit
|
5 |
+
base_model: microsoft/speecht5_tts
|
6 |
+
tags:
|
7 |
+
- TTS,
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- lj_speech
|
11 |
+
model-index:
|
12 |
+
- name: SpeechT5 TTS LJ_Speech
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# SpeechT5 TTS LJ_Speech
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the lj_speech dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3659
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 1e-05
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_steps: 500
|
51 |
+
- training_steps: 10000
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
58 |
+
| 0.4059 | 2.7137 | 1000 | 0.3729 |
|
59 |
+
| 0.3927 | 5.4274 | 2000 | 0.3707 |
|
60 |
+
| 0.3982 | 8.1411 | 3000 | 0.3696 |
|
61 |
+
| 0.4006 | 10.8548 | 4000 | 0.3682 |
|
62 |
+
| 0.3869 | 13.5685 | 5000 | 0.3669 |
|
63 |
+
| 0.395 | 16.2822 | 6000 | 0.3669 |
|
64 |
+
| 0.4012 | 18.9959 | 7000 | 0.3666 |
|
65 |
+
| 0.3858 | 21.7096 | 8000 | 0.3662 |
|
66 |
+
| 0.3864 | 24.4233 | 9000 | 0.3658 |
|
67 |
+
| 0.3982 | 27.1370 | 10000 | 0.3659 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.41.0.dev0
|
73 |
+
- Pytorch 2.3.0+cu121
|
74 |
+
- Datasets 2.19.0
|
75 |
+
- 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": "4.41.0.dev0"
|
9 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1777dd726706ba17146e6122f48163dd6f1355ecbb129aeefd8508eb40611149
|
3 |
size 577789320
|