Hugging Face's logo

karline
/
tts_me_realCS_dataset

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
Metrics Community
karline commited on
Commit
20ee903
·
verified ·
1 Parent(s): ea88291

End of training

Browse files
Files changed (4) hide show
  1. README.md +113 -0
  2. generation_config.json +9 -0
  3. model.safetensors +1 -1
  4. runs/Jan28_15-18-39_asr/events.out.tfevents.1738057720.asr.175915.0 +2 -2
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/speecht5_tts
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - audiofolder
9
+ model-index:
10
+ - name: tts_me_realCS_dataset
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # tts_me_realCS_dataset
18
+
19
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the audiofolder dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4043
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 2
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 32
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 100
49
+ - training_steps: 5000
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.5661 | 0.1808 | 100 | 0.5027 |
57
+ | 0.5194 | 0.3616 | 200 | 0.4732 |
58
+ | 0.4983 | 0.5424 | 300 | 0.4571 |
59
+ | 0.4966 | 0.7232 | 400 | 0.4554 |
60
+ | 0.4867 | 0.9040 | 500 | 0.4494 |
61
+ | 0.4808 | 1.0832 | 600 | 0.4493 |
62
+ | 0.4806 | 1.2640 | 700 | 0.4455 |
63
+ | 0.4763 | 1.4447 | 800 | 0.4439 |
64
+ | 0.4733 | 1.6255 | 900 | 0.4427 |
65
+ | 0.4756 | 1.8063 | 1000 | 0.4377 |
66
+ | 0.4689 | 1.9871 | 1100 | 0.4357 |
67
+ | 0.4658 | 2.1663 | 1200 | 0.4343 |
68
+ | 0.4637 | 2.3471 | 1300 | 0.4342 |
69
+ | 0.462 | 2.5279 | 1400 | 0.4299 |
70
+ | 0.4621 | 2.7087 | 1500 | 0.4258 |
71
+ | 0.4571 | 2.8895 | 1600 | 0.4234 |
72
+ | 0.4539 | 3.0687 | 1700 | 0.4214 |
73
+ | 0.4485 | 3.2495 | 1800 | 0.4184 |
74
+ | 0.4502 | 3.4303 | 1900 | 0.4173 |
75
+ | 0.4493 | 3.6111 | 2000 | 0.4160 |
76
+ | 0.4459 | 3.7919 | 2100 | 0.4156 |
77
+ | 0.444 | 3.9727 | 2200 | 0.4144 |
78
+ | 0.4405 | 4.1519 | 2300 | 0.4129 |
79
+ | 0.4411 | 4.3327 | 2400 | 0.4141 |
80
+ | 0.4403 | 4.5134 | 2500 | 0.4120 |
81
+ | 0.4411 | 4.6942 | 2600 | 0.4118 |
82
+ | 0.4396 | 4.8750 | 2700 | 0.4091 |
83
+ | 0.4345 | 5.0542 | 2800 | 0.4085 |
84
+ | 0.4348 | 5.2350 | 2900 | 0.4089 |
85
+ | 0.4363 | 5.4158 | 3000 | 0.4088 |
86
+ | 0.4325 | 5.5966 | 3100 | 0.4088 |
87
+ | 0.4325 | 5.7774 | 3200 | 0.4081 |
88
+ | 0.4345 | 5.9582 | 3300 | 0.4080 |
89
+ | 0.4332 | 6.1374 | 3400 | 0.4076 |
90
+ | 0.4321 | 6.3182 | 3500 | 0.4067 |
91
+ | 0.4273 | 6.4990 | 3600 | 0.4071 |
92
+ | 0.4309 | 6.6798 | 3700 | 0.4079 |
93
+ | 0.432 | 6.8606 | 3800 | 0.4057 |
94
+ | 0.4145 | 7.0398 | 3900 | 0.4057 |
95
+ | 0.4277 | 7.2206 | 4000 | 0.4053 |
96
+ | 0.4275 | 7.4014 | 4100 | 0.4045 |
97
+ | 0.4307 | 7.5821 | 4200 | 0.4054 |
98
+ | 0.4252 | 7.7629 | 4300 | 0.4044 |
99
+ | 0.4306 | 7.9437 | 4400 | 0.4048 |
100
+ | 0.4257 | 8.1229 | 4500 | 0.4042 |
101
+ | 0.4332 | 8.3037 | 4600 | 0.4049 |
102
+ | 0.4269 | 8.4845 | 4700 | 0.4041 |
103
+ | 0.429 | 8.6653 | 4800 | 0.4033 |
104
+ | 0.4245 | 8.8461 | 4900 | 0.4043 |
105
+ | 0.4111 | 9.0253 | 5000 | 0.4043 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.48.0
111
+ - Pytorch 2.2.1
112
+ - Datasets 3.2.0
113
+ - Tokenizers 0.21.0
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": "4.48.0"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f4bf3a9437d5218137ca155ad5853bc73a66657a893e1aa24826a14062440c8
3
  size 577930632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c836ea070014f4d04c8e36d5f37b56cc1503cd175275b7d6e611b4afb117578
3
  size 577930632
runs/Jan28_15-18-39_asr/events.out.tfevents.1738057720.asr.175915.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8644aebafdc37a3a313f17a6ae67b5d5e48955146d938e123241c79d9361f127
3
- size 31144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076a3f06a5e988f2a547e1064c7264b975dac377e3cfaace69fcd4eb91f6f6c9
3
+ size 62718