Hugging Face's logo

Shaju07
/
urdu_tts_0.1

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Shaju07 commited on
Commit
68b4db8
·
verified ·
1 Parent(s): c4b6bc5

End of training

Browse files
Files changed (4) hide show
  1. README.md +111 -0
  2. generation_config.json +9 -0
  3. model.safetensors +1 -1
  4. runs/Mar05_13-23-40_d07dcfcc6745/events.out.tfevents.1741181067.d07dcfcc6745.252.0 +2 -2
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/speecht5_tts
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: urdu_tts_0.1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # urdu_tts_0.1
16
+
17
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4299
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 32
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 5000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.565 | 0.5051 | 100 | 0.5047 |
55
+ | 0.5258 | 1.0101 | 200 | 0.4888 |
56
+ | 0.496 | 1.5152 | 300 | 0.4695 |
57
+ | 0.4882 | 2.0202 | 400 | 0.4558 |
58
+ | 0.4839 | 2.5253 | 500 | 0.4531 |
59
+ | 0.4781 | 3.0303 | 600 | 0.4487 |
60
+ | 0.4715 | 3.5354 | 700 | 0.4446 |
61
+ | 0.4657 | 4.0404 | 800 | 0.4408 |
62
+ | 0.4582 | 4.5455 | 900 | 0.4397 |
63
+ | 0.4568 | 5.0505 | 1000 | 0.4379 |
64
+ | 0.4552 | 5.5556 | 1100 | 0.4427 |
65
+ | 0.451 | 6.0606 | 1200 | 0.4333 |
66
+ | 0.4512 | 6.5657 | 1300 | 0.4327 |
67
+ | 0.4441 | 7.0707 | 1400 | 0.4321 |
68
+ | 0.4453 | 7.5758 | 1500 | 0.4313 |
69
+ | 0.4422 | 8.0808 | 1600 | 0.4314 |
70
+ | 0.4405 | 8.5859 | 1700 | 0.4262 |
71
+ | 0.4427 | 9.0909 | 1800 | 0.4306 |
72
+ | 0.4362 | 9.5960 | 1900 | 0.4315 |
73
+ | 0.4306 | 10.1010 | 2000 | 0.4239 |
74
+ | 0.4328 | 10.6061 | 2100 | 0.4250 |
75
+ | 0.425 | 11.1111 | 2200 | 0.4272 |
76
+ | 0.4271 | 11.6162 | 2300 | 0.4312 |
77
+ | 0.4246 | 12.1212 | 2400 | 0.4259 |
78
+ | 0.424 | 12.6263 | 2500 | 0.4253 |
79
+ | 0.4209 | 13.1313 | 2600 | 0.4231 |
80
+ | 0.4204 | 13.6364 | 2700 | 0.4295 |
81
+ | 0.4135 | 14.1414 | 2800 | 0.4228 |
82
+ | 0.4162 | 14.6465 | 2900 | 0.4180 |
83
+ | 0.4169 | 15.1515 | 3000 | 0.4254 |
84
+ | 0.4136 | 15.6566 | 3100 | 0.4228 |
85
+ | 0.4102 | 16.1616 | 3200 | 0.4241 |
86
+ | 0.4107 | 16.6667 | 3300 | 0.4213 |
87
+ | 0.4104 | 17.1717 | 3400 | 0.4281 |
88
+ | 0.409 | 17.6768 | 3500 | 0.4240 |
89
+ | 0.4083 | 18.1818 | 3600 | 0.4264 |
90
+ | 0.405 | 18.6869 | 3700 | 0.4260 |
91
+ | 0.4035 | 19.1919 | 3800 | 0.4265 |
92
+ | 0.4054 | 19.6970 | 3900 | 0.4271 |
93
+ | 0.4047 | 20.2020 | 4000 | 0.4305 |
94
+ | 0.4031 | 20.7071 | 4100 | 0.4304 |
95
+ | 0.4044 | 21.2121 | 4200 | 0.4289 |
96
+ | 0.4016 | 21.7172 | 4300 | 0.4297 |
97
+ | 0.4005 | 22.2222 | 4400 | 0.4275 |
98
+ | 0.4084 | 22.7273 | 4500 | 0.4291 |
99
+ | 0.4026 | 23.2323 | 4600 | 0.4284 |
100
+ | 0.402 | 23.7374 | 4700 | 0.4288 |
101
+ | 0.4002 | 24.2424 | 4800 | 0.4294 |
102
+ | 0.401 | 24.7475 | 4900 | 0.4298 |
103
+ | 0.398 | 25.2525 | 5000 | 0.4299 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.48.3
109
+ - Pytorch 2.5.1+cu124
110
+ - Datasets 3.3.2
111
+ - 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": "4.48.3"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b8eb7984686aa90638a7731c1606d6b55e25305e309a48c86cfd7a909341b4e
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020840b71386758c5de4322730ee2ff9e8ce0bcfabbf3ee5ed8f38d883319706
3
  size 577789320
runs/Mar05_13-23-40_d07dcfcc6745/events.out.tfevents.1741181067.d07dcfcc6745.252.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e821468dbbdd017702b90d4a8e246ab5ddb83f6e028a4dbd65d449363b63ebb
3
- size 62388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b42c2fe433aa15b0920b075f17f621212eeaadf535e36ed174c63c4ae42cec
3
+ size 62742