flavioegoncalves commited on
Commit
63c547f
1 Parent(s): 7cff14c

End of training

Browse files
README.md CHANGED
@@ -1,3 +1,69 @@
1
  ---
 
 
2
  license: mit
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - pt
4
  license: mit
5
+ base_model: microsoft/speecht5_tts
6
+ tags:
7
+ - tts
8
+ - generated_from_trainer
9
+ datasets:
10
+ - multilingual_librispeech
11
+ model-index:
12
+ - name: SpeechT5 TTS Portuguese
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 Portuguese
20
+
21
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the MultilingualLibrispeech dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.3677
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: 4
44
+ - eval_batch_size: 2
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 8
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
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.4263 | 3.88 | 1000 | 0.3850 |
59
+ | 0.4078 | 7.76 | 2000 | 0.3719 |
60
+ | 0.4017 | 11.63 | 3000 | 0.3694 |
61
+ | 0.403 | 15.51 | 4000 | 0.3677 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.38.0.dev0
67
+ - Pytorch 2.1.0+cu121
68
+ - Datasets 2.16.1
69
+ - Tokenizers 0.15.0
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": "4.38.0.dev0"
9
+ }
runs/Jan21_12-27-05_8effc0160e8f/events.out.tfevents.1705840041.8effc0160e8f.539.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a4d82aaa306211ccf31a108fa3b524278fd43363565ce726531d56f122aa2cd
3
- size 32199
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:663aa956534afed748ec7d3d23bab013918e8a6a873748e257b6fa496419df06
3
+ size 32553