yhk commited on
Commit
48c9969
1 Parent(s): 89ba486

End of training

Browse files
Files changed (2) hide show
  1. README.md +68 -0
  2. generation_config.json +9 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - nl
4
+ license: mit
5
+ base_model: microsoft/speecht5_tts
6
+ tags:
7
+ - test
8
+ - generated_from_trainer
9
+ datasets:
10
+ - facebook/voxpopuli
11
+ model-index:
12
+ - name: SpeechT5 TTS Dutch
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 Dutch
20
+
21
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4590
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: 4000
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 0.5205 | 4.3 | 1000 | 0.4807 |
58
+ | 0.5018 | 8.6 | 2000 | 0.4657 |
59
+ | 0.4992 | 12.9 | 3000 | 0.4607 |
60
+ | 0.4939 | 17.2 | 4000 | 0.4590 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.34.0.dev0
66
+ - Pytorch 2.0.1
67
+ - Datasets 2.14.5
68
+ - Tokenizers 0.13.3
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": "4.34.0.dev0"
9
+ }