Hugging Face's logo

Meitt
/
results

Text-to-Audio
Transformers
TensorBoard
Safetensors
fl
speecht5
Tets only
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Meitt commited on
Commit
56d79b6
•
1 Parent(s): becc3e2

End of training

Browse files
Files changed (4) hide show
  1. README.md +75 -0
  2. README.md.bak +78 -0
  3. generation_config.json +9 -0
  4. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - fl
4
+ license: mit
5
+ base_model: microsoft/speecht5_tts
6
+ tags:
7
+ - Tets only
8
+ - generated_from_trainer
9
+ datasets:
10
+ - mewu/test
11
+ model-index:
12
+ - name: Mewu custom
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
+ # Mewu custom
20
+
21
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the mewu dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.4956
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: 0.001
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: 1000
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:--------:|:----:|:---------------:|
58
+ | 0.4967 | 66.6667 | 100 | 0.4655 |
59
+ | 0.504 | 133.3333 | 200 | 0.4540 |
60
+ | 0.5434 | 200.0 | 300 | 0.6293 |
61
+ | 1.5883 | 266.6667 | 400 | 1.5112 |
62
+ | 1.5286 | 333.3333 | 500 | 1.5048 |
63
+ | 1.4761 | 400.0 | 600 | 1.5227 |
64
+ | 1.4458 | 466.6667 | 700 | 1.4967 |
65
+ | 1.4453 | 533.3333 | 800 | 1.4935 |
66
+ | 1.4446 | 600.0 | 900 | 1.4960 |
67
+ | 1.4451 | 666.6667 | 1000 | 1.4956 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.40.1
73
+ - Pytorch 2.3.0+cu118
74
+ - Datasets 2.19.1
75
+ - Tokenizers 0.19.1
README.md.bak ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - fl
4
+ license: mit
5
+ base_model: microsoft/speecht5_tts
6
+ tags:
7
+ - Tets only
8
+ - speech
9
+ - ''
10
+ - generated_from_trainer
11
+ - Test only
12
+ datasets:
13
+ - mewu/test
14
+ model-index:
15
+ - name: Mewu custom
16
+ results: []
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # Mewu custom
23
+
24
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the mewu dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 1.4956
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 0.001
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - gradient_accumulation_steps: 2
50
+ - total_train_batch_size: 32
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
+ - training_steps: 1000
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss |
60
+ |:-------------:|:--------:|:----:|:---------------:|
61
+ | 0.4967 | 66.6667 | 100 | 0.4655 |
62
+ | 0.504 | 133.3333 | 200 | 0.4540 |
63
+ | 0.5434 | 200.0 | 300 | 0.6293 |
64
+ | 1.5883 | 266.6667 | 400 | 1.5112 |
65
+ | 1.5286 | 333.3333 | 500 | 1.5048 |
66
+ | 1.4761 | 400.0 | 600 | 1.5227 |
67
+ | 1.4458 | 466.6667 | 700 | 1.4967 |
68
+ | 1.4453 | 533.3333 | 800 | 1.4935 |
69
+ | 1.4446 | 600.0 | 900 | 1.4960 |
70
+ | 1.4451 | 666.6667 | 1000 | 1.4956 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.40.1
76
+ - Pytorch 2.3.0+cu118
77
+ - Datasets 2.19.1
78
+ - 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": "4.40.1"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6191be509e658b8805d4b1c90398032c67981223b30213d449645815dfffb5ca
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ff0ae6c5c6f3eb4a42fec29b766d020d7ecdf65b9fc76f6fe7cf58dab2a60a
3
  size 577789320