Hugging Face's logo

ai557
/
speecht5_finetuned_nepali

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
Metrics Community
ai557 commited on
Commit
c1e83b7
·
verified ·
1 Parent(s): 8911553

End of training

Browse files
Files changed (7) hide show
  1. README.md +87 -26
  2. model.safetensors +1 -1
  3. runs/Jul06_16-28-29_hem-MS-7D88/events.out.tfevents.1751798610.hem-MS-7D88.1869533.0 +3 -0
  4. runs/Jul06_16-29-35_hem-MS-7D88/events.out.tfevents.1751798676.hem-MS-7D88.1875155.0 +3 -0
  5. runs/Jul06_16-30-29_hem-MS-7D88/events.out.tfevents.1751798730.hem-MS-7D88.1879902.0 +3 -0
  6. runs/Jul06_16-36-46_hem-MS-7D88/events.out.tfevents.1751799107.hem-MS-7D88.1910708.0 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.2269
22
 
23
  ## Model description
24
 
@@ -37,40 +37,101 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0001
41
- - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
 
 
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: linear
46
- - lr_scheduler_warmup_steps: 200
47
- - training_steps: 5000
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.3938 | 250.0 | 250 | 0.8686 |
55
- | 0.2998 | 500.0 | 500 | 1.1800 |
56
- | 0.2236 | 750.0 | 750 | 1.1533 |
57
- | 0.2311 | 1000.0 | 1000 | 1.1681 |
58
- | 0.1915 | 1250.0 | 1250 | 1.2941 |
59
- | 0.167 | 1500.0 | 1500 | 1.2205 |
60
- | 0.1581 | 1750.0 | 1750 | 1.1918 |
61
- | 0.1101 | 2000.0 | 2000 | 1.1861 |
62
- | 0.1095 | 2250.0 | 2250 | 1.2361 |
63
- | 0.1006 | 2500.0 | 2500 | 1.2297 |
64
- | 0.105 | 2750.0 | 2750 | 1.2556 |
65
- | 0.1499 | 3000.0 | 3000 | 1.1880 |
66
- | 0.1018 | 3250.0 | 3250 | 1.2641 |
67
- | 0.1157 | 3500.0 | 3500 | 1.2431 |
68
- | 0.0873 | 3750.0 | 3750 | 1.2431 |
69
- | 0.071 | 4000.0 | 4000 | 1.2593 |
70
- | 0.0983 | 4250.0 | 4250 | 1.2721 |
71
- | 0.0982 | 4500.0 | 4500 | 1.2339 |
72
- | 0.0642 | 4750.0 | 4750 | 1.2357 |
73
- | 0.0664 | 5000.0 | 5000 | 1.2269 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8166
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
  - eval_batch_size: 8
43
  - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 16
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: 1000
49
+ - training_steps: 8000
 
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.2436 | 100.0 | 100 | 1.1269 |
56
+ | 0.1083 | 200.0 | 200 | 0.9825 |
57
+ | 0.134 | 300.0 | 300 | 1.0018 |
58
+ | 0.091 | 400.0 | 400 | 0.9214 |
59
+ | 0.0853 | 500.0 | 500 | 0.8461 |
60
+ | 0.0574 | 600.0 | 600 | 0.8854 |
61
+ | 0.048 | 700.0 | 700 | 0.9222 |
62
+ | 0.0478 | 800.0 | 800 | 0.8826 |
63
+ | 0.0455 | 900.0 | 900 | 0.9160 |
64
+ | 0.0458 | 1000.0 | 1000 | 0.8953 |
65
+ | 0.0432 | 1100.0 | 1100 | 0.9311 |
66
+ | 0.0378 | 1200.0 | 1200 | 0.9394 |
67
+ | 0.0453 | 1300.0 | 1300 | 0.9039 |
68
+ | 0.0344 | 1400.0 | 1400 | 0.8747 |
69
+ | 0.0408 | 1500.0 | 1500 | 0.8577 |
70
+ | 0.0348 | 1600.0 | 1600 | 0.8911 |
71
+ | 0.035 | 1700.0 | 1700 | 0.9116 |
72
+ | 0.0391 | 1800.0 | 1800 | 0.9473 |
73
+ | 0.0293 | 1900.0 | 1900 | 0.9689 |
74
+ | 0.0331 | 2000.0 | 2000 | 0.8895 |
75
+ | 0.0342 | 2100.0 | 2100 | 0.9130 |
76
+ | 0.0395 | 2200.0 | 2200 | 0.8804 |
77
+ | 0.0309 | 2300.0 | 2300 | 0.9170 |
78
+ | 0.0452 | 2400.0 | 2400 | 0.9573 |
79
+ | 0.028 | 2500.0 | 2500 | 0.9134 |
80
+ | 0.0301 | 2600.0 | 2600 | 0.8434 |
81
+ | 0.0253 | 2700.0 | 2700 | 0.9187 |
82
+ | 0.0296 | 2800.0 | 2800 | 0.9304 |
83
+ | 0.029 | 2900.0 | 2900 | 0.8895 |
84
+ | 0.0309 | 3000.0 | 3000 | 0.8393 |
85
+ | 0.0301 | 3100.0 | 3100 | 0.8827 |
86
+ | 0.0291 | 3200.0 | 3200 | 0.9043 |
87
+ | 0.0287 | 3300.0 | 3300 | 0.9155 |
88
+ | 0.0249 | 3400.0 | 3400 | 0.8606 |
89
+ | 0.0242 | 3500.0 | 3500 | 0.8851 |
90
+ | 0.0254 | 3600.0 | 3600 | 0.8624 |
91
+ | 0.0243 | 3700.0 | 3700 | 0.8141 |
92
+ | 0.0267 | 3800.0 | 3800 | 0.8290 |
93
+ | 0.0229 | 3900.0 | 3900 | 0.9157 |
94
+ | 0.0232 | 4000.0 | 4000 | 0.8753 |
95
+ | 0.0274 | 4100.0 | 4100 | 0.8536 |
96
+ | 0.0222 | 4200.0 | 4200 | 0.8884 |
97
+ | 0.022 | 4300.0 | 4300 | 0.7999 |
98
+ | 0.022 | 4400.0 | 4400 | 0.8284 |
99
+ | 0.0417 | 4500.0 | 4500 | 0.8500 |
100
+ | 0.0254 | 4600.0 | 4600 | 0.8911 |
101
+ | 0.0409 | 4700.0 | 4700 | 0.8149 |
102
+ | 0.0254 | 4800.0 | 4800 | 0.8783 |
103
+ | 0.0239 | 4900.0 | 4900 | 0.9306 |
104
+ | 0.0214 | 5000.0 | 5000 | 0.7524 |
105
+ | 0.0259 | 5100.0 | 5100 | 0.8071 |
106
+ | 0.0209 | 5200.0 | 5200 | 0.8557 |
107
+ | 0.021 | 5300.0 | 5300 | 0.8289 |
108
+ | 0.0246 | 5400.0 | 5400 | 0.7950 |
109
+ | 0.0213 | 5500.0 | 5500 | 0.7693 |
110
+ | 0.0281 | 5600.0 | 5600 | 0.7930 |
111
+ | 0.0243 | 5700.0 | 5700 | 0.7917 |
112
+ | 0.024 | 5800.0 | 5800 | 0.8430 |
113
+ | 0.0208 | 5900.0 | 5900 | 0.7643 |
114
+ | 0.0237 | 6000.0 | 6000 | 0.7629 |
115
+ | 0.0221 | 6100.0 | 6100 | 0.7900 |
116
+ | 0.0217 | 6200.0 | 6200 | 0.8108 |
117
+ | 0.023 | 6300.0 | 6300 | 0.7847 |
118
+ | 0.0228 | 6400.0 | 6400 | 0.8063 |
119
+ | 0.0303 | 6500.0 | 6500 | 0.7035 |
120
+ | 0.0229 | 6600.0 | 6600 | 0.8152 |
121
+ | 0.0224 | 6700.0 | 6700 | 0.7836 |
122
+ | 0.0204 | 6800.0 | 6800 | 0.8284 |
123
+ | 0.0206 | 6900.0 | 6900 | 0.8586 |
124
+ | 0.0195 | 7000.0 | 7000 | 0.7827 |
125
+ | 0.023 | 7100.0 | 7100 | 0.7622 |
126
+ | 0.028 | 7200.0 | 7200 | 0.8719 |
127
+ | 0.0196 | 7300.0 | 7300 | 0.8178 |
128
+ | 0.024 | 7400.0 | 7400 | 0.8933 |
129
+ | 0.0296 | 7500.0 | 7500 | 0.8023 |
130
+ | 0.0255 | 7600.0 | 7600 | 0.8234 |
131
+ | 0.0205 | 7700.0 | 7700 | 0.7731 |
132
+ | 0.0222 | 7800.0 | 7800 | 0.8332 |
133
+ | 0.0195 | 7900.0 | 7900 | 0.8543 |
134
+ | 0.0238 | 8000.0 | 8000 | 0.8166 |
135
 
136
 
137
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcc84ac87e5ce6fa2359b92557c9fd98ac7cf60f1d4ae65c2c704792a4117b32
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35374a1830d81b851477d78e0fa5b073e9dd2782c9a70cd93d72304ef58ec5a
3
  size 577789320
runs/Jul06_16-28-29_hem-MS-7D88/events.out.tfevents.1751798610.hem-MS-7D88.1869533.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7aa52a5a5dfd4d7cce1ee2fa49982c7d00fbff7d16b4e5356100123fff32cc1
3
+ size 6590
runs/Jul06_16-29-35_hem-MS-7D88/events.out.tfevents.1751798676.hem-MS-7D88.1875155.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e8d81f8908a4f84c9b92f0ba063d0ee4b1b8e776de250be0788497c668c848
3
+ size 6590
runs/Jul06_16-30-29_hem-MS-7D88/events.out.tfevents.1751798730.hem-MS-7D88.1879902.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135846c8ad99dbee17ab554b4585ce7529a67a4297f6a17d6cff2a74b158223d
3
+ size 193779
runs/Jul06_16-36-46_hem-MS-7D88/events.out.tfevents.1751799107.hem-MS-7D88.1910708.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889a581688a2bd006b9e4a6fac60b1a15fe05009466d681cf16034d553fb18ae
3
+ size 366117
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d502c9137db5104e0c354fb0db7d74952b6ebb45319965e7ad963190c574634
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a702a12e7b1c29fee253cb92c14f0f9856319d46e1a6ebf94664031e5c9193a
3
  size 5905