Hawoly18 commited on
Commit
70dd6ca
1 Parent(s): 38e81ce

End of training

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.4769
20
 
21
  ## Model description
22
 
@@ -49,93 +49,93 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 2.1638 | 0.0963 | 50 | 1.0066 |
55
- | 2.0092 | 0.1927 | 100 | 0.9555 |
56
- | 1.7858 | 0.2890 | 150 | 0.9100 |
57
- | 1.8592 | 0.3854 | 200 | 0.8772 |
58
- | 1.778 | 0.4817 | 250 | 0.8337 |
59
- | 1.6383 | 0.5780 | 300 | 0.7854 |
60
- | 1.4971 | 0.6744 | 350 | 0.6216 |
61
- | 1.2996 | 0.7707 | 400 | 0.5678 |
62
- | 1.2728 | 0.8671 | 450 | 0.5555 |
63
- | 1.2295 | 0.9634 | 500 | 0.5388 |
64
- | 1.1974 | 1.0597 | 550 | 0.5332 |
65
- | 1.1524 | 1.1561 | 600 | 0.5261 |
66
- | 1.2034 | 1.2524 | 650 | 0.5243 |
67
- | 1.1313 | 1.3487 | 700 | 0.5137 |
68
- | 1.1011 | 1.4451 | 750 | 0.5121 |
69
- | 1.1376 | 1.5414 | 800 | 0.5112 |
70
- | 1.142 | 1.6378 | 850 | 0.5097 |
71
- | 1.1685 | 1.7341 | 900 | 0.5035 |
72
- | 1.122 | 1.8304 | 950 | 0.5030 |
73
- | 1.117 | 1.9268 | 1000 | 0.5075 |
74
- | 1.1164 | 2.0231 | 1050 | 0.5011 |
75
- | 1.1186 | 2.1195 | 1100 | 0.4997 |
76
- | 1.102 | 2.2158 | 1150 | 0.4999 |
77
- | 1.0753 | 2.3121 | 1200 | 0.4995 |
78
- | 1.0459 | 2.4085 | 1250 | 0.4950 |
79
- | 1.1395 | 2.5048 | 1300 | 0.4967 |
80
- | 1.086 | 2.6012 | 1350 | 0.4914 |
81
- | 1.0647 | 2.6975 | 1400 | 0.4922 |
82
- | 1.0779 | 2.7938 | 1450 | 0.4925 |
83
- | 1.0814 | 2.8902 | 1500 | 0.4885 |
84
- | 1.092 | 2.9865 | 1550 | 0.4909 |
85
- | 1.0609 | 3.0829 | 1600 | 0.4883 |
86
- | 1.0517 | 3.1792 | 1650 | 0.4903 |
87
- | 1.0954 | 3.2755 | 1700 | 0.4886 |
88
- | 1.0431 | 3.3719 | 1750 | 0.4903 |
89
- | 1.0756 | 3.4682 | 1800 | 0.4914 |
90
- | 1.0806 | 3.5645 | 1850 | 0.4835 |
91
- | 1.0592 | 3.6609 | 1900 | 0.4891 |
92
- | 1.054 | 3.7572 | 1950 | 0.4906 |
93
- | 1.0297 | 3.8536 | 2000 | 0.4863 |
94
- | 1.0461 | 3.9499 | 2050 | 0.4833 |
95
- | 1.0244 | 4.0462 | 2100 | 0.4836 |
96
- | 1.0341 | 4.1426 | 2150 | 0.4826 |
97
- | 1.0287 | 4.2389 | 2200 | 0.4806 |
98
- | 1.026 | 4.3353 | 2250 | 0.4831 |
99
- | 1.0354 | 4.4316 | 2300 | 0.4850 |
100
- | 1.0665 | 4.5279 | 2350 | 0.4824 |
101
- | 1.0291 | 4.6243 | 2400 | 0.4800 |
102
- | 1.0425 | 4.7206 | 2450 | 0.4791 |
103
- | 1.0367 | 4.8170 | 2500 | 0.4796 |
104
- | 1.0393 | 4.9133 | 2550 | 0.4814 |
105
- | 1.0301 | 5.0096 | 2600 | 0.4799 |
106
- | 1.0431 | 5.1060 | 2650 | 0.4790 |
107
- | 1.0261 | 5.2023 | 2700 | 0.4791 |
108
- | 1.05 | 5.2987 | 2750 | 0.4804 |
109
- | 1.0296 | 5.3950 | 2800 | 0.4794 |
110
- | 1.0296 | 5.4913 | 2850 | 0.4805 |
111
- | 1.0214 | 5.5877 | 2900 | 0.4792 |
112
- | 1.0277 | 5.6840 | 2950 | 0.4781 |
113
- | 1.0355 | 5.7803 | 3000 | 0.4764 |
114
- | 1.0325 | 5.8767 | 3050 | 0.4779 |
115
- | 1.0206 | 5.9730 | 3100 | 0.4768 |
116
- | 1.0316 | 6.0694 | 3150 | 0.4793 |
117
- | 1.0426 | 6.1657 | 3200 | 0.4771 |
118
- | 1.0562 | 6.2620 | 3250 | 0.4786 |
119
- | 1.0242 | 6.3584 | 3300 | 0.4792 |
120
- | 1.0144 | 6.4547 | 3350 | 0.4788 |
121
- | 1.0335 | 6.5511 | 3400 | 0.4761 |
122
- | 0.9995 | 6.6474 | 3450 | 0.4757 |
123
- | 1.0119 | 6.7437 | 3500 | 0.4772 |
124
- | 1.0355 | 6.8401 | 3550 | 0.4789 |
125
- | 0.9858 | 6.9364 | 3600 | 0.4767 |
126
- | 1.0327 | 7.0328 | 3650 | 0.4757 |
127
- | 1.0355 | 7.1291 | 3700 | 0.4746 |
128
- | 0.9974 | 7.2254 | 3750 | 0.4757 |
129
- | 1.0296 | 7.3218 | 3800 | 0.4761 |
130
- | 1.0033 | 7.4181 | 3850 | 0.4759 |
131
- | 1.0013 | 7.5145 | 3900 | 0.4751 |
132
- | 1.0086 | 7.6108 | 3950 | 0.4756 |
133
- | 1.0191 | 7.7071 | 4000 | 0.4769 |
134
 
135
 
136
  ### Framework versions
137
 
138
- - Transformers 4.46.0.dev0
139
  - Pytorch 2.4.0
140
  - Datasets 3.0.1
141
  - Tokenizers 0.20.0
 
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: 0.2993
20
 
21
  ## Model description
22
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 1.1192 | 0.5952 | 50 | 0.4722 |
55
+ | 0.9979 | 1.1905 | 100 | 0.4139 |
56
+ | 0.8933 | 1.7857 | 150 | 0.3900 |
57
+ | 0.8718 | 2.3810 | 200 | 0.3818 |
58
+ | 0.8246 | 2.9762 | 250 | 0.3758 |
59
+ | 0.8062 | 3.5714 | 300 | 0.3615 |
60
+ | 0.7931 | 4.1667 | 350 | 0.3546 |
61
+ | 0.756 | 4.7619 | 400 | 0.3469 |
62
+ | 0.7462 | 5.3571 | 450 | 0.3393 |
63
+ | 0.7311 | 5.9524 | 500 | 0.3358 |
64
+ | 0.7298 | 6.5476 | 550 | 0.3315 |
65
+ | 0.7234 | 7.1429 | 600 | 0.3300 |
66
+ | 0.7199 | 7.7381 | 650 | 0.3287 |
67
+ | 0.697 | 8.3333 | 700 | 0.3250 |
68
+ | 0.7006 | 8.9286 | 750 | 0.3231 |
69
+ | 0.7081 | 9.5238 | 800 | 0.3218 |
70
+ | 0.6998 | 10.1190 | 850 | 0.3196 |
71
+ | 0.7074 | 10.7143 | 900 | 0.3202 |
72
+ | 0.6831 | 11.3095 | 950 | 0.3161 |
73
+ | 0.6899 | 11.9048 | 1000 | 0.3169 |
74
+ | 0.6935 | 12.5 | 1050 | 0.3160 |
75
+ | 0.6778 | 13.0952 | 1100 | 0.3145 |
76
+ | 0.6701 | 13.6905 | 1150 | 0.3122 |
77
+ | 0.6792 | 14.2857 | 1200 | 0.3121 |
78
+ | 0.6668 | 14.8810 | 1250 | 0.3117 |
79
+ | 0.6682 | 15.4762 | 1300 | 0.3120 |
80
+ | 0.6742 | 16.0714 | 1350 | 0.3103 |
81
+ | 0.6759 | 16.6667 | 1400 | 0.3103 |
82
+ | 0.6776 | 17.2619 | 1450 | 0.3100 |
83
+ | 0.6699 | 17.8571 | 1500 | 0.3099 |
84
+ | 0.6744 | 18.4524 | 1550 | 0.3092 |
85
+ | 0.6636 | 19.0476 | 1600 | 0.3083 |
86
+ | 0.6552 | 19.6429 | 1650 | 0.3067 |
87
+ | 0.6618 | 20.2381 | 1700 | 0.3074 |
88
+ | 0.6482 | 20.8333 | 1750 | 0.3059 |
89
+ | 0.6684 | 21.4286 | 1800 | 0.3063 |
90
+ | 0.6726 | 22.0238 | 1850 | 0.3060 |
91
+ | 0.648 | 22.6190 | 1900 | 0.3053 |
92
+ | 0.6542 | 23.2143 | 1950 | 0.3043 |
93
+ | 0.6516 | 23.8095 | 2000 | 0.3050 |
94
+ | 0.6654 | 24.4048 | 2050 | 0.3059 |
95
+ | 0.6556 | 25.0 | 2100 | 0.3050 |
96
+ | 0.6493 | 25.5952 | 2150 | 0.3051 |
97
+ | 0.6504 | 26.1905 | 2200 | 0.3033 |
98
+ | 0.6463 | 26.7857 | 2250 | 0.3033 |
99
+ | 0.655 | 27.3810 | 2300 | 0.3028 |
100
+ | 0.6474 | 27.9762 | 2350 | 0.3030 |
101
+ | 0.6434 | 28.5714 | 2400 | 0.3022 |
102
+ | 0.6427 | 29.1667 | 2450 | 0.3027 |
103
+ | 0.6611 | 29.7619 | 2500 | 0.3030 |
104
+ | 0.6536 | 30.3571 | 2550 | 0.3026 |
105
+ | 0.6478 | 30.9524 | 2600 | 0.3011 |
106
+ | 0.6471 | 31.5476 | 2650 | 0.3021 |
107
+ | 0.6424 | 32.1429 | 2700 | 0.3014 |
108
+ | 0.6424 | 32.7381 | 2750 | 0.3012 |
109
+ | 0.645 | 33.3333 | 2800 | 0.3010 |
110
+ | 0.6454 | 33.9286 | 2850 | 0.3010 |
111
+ | 0.6373 | 34.5238 | 2900 | 0.3006 |
112
+ | 0.6409 | 35.1190 | 2950 | 0.3005 |
113
+ | 0.6382 | 35.7143 | 3000 | 0.3007 |
114
+ | 0.6377 | 36.3095 | 3050 | 0.3005 |
115
+ | 0.643 | 36.9048 | 3100 | 0.3007 |
116
+ | 0.6383 | 37.5 | 3150 | 0.2999 |
117
+ | 0.6396 | 38.0952 | 3200 | 0.2998 |
118
+ | 0.6413 | 38.6905 | 3250 | 0.3006 |
119
+ | 0.6368 | 39.2857 | 3300 | 0.2998 |
120
+ | 0.6452 | 39.8810 | 3350 | 0.3006 |
121
+ | 0.6425 | 40.4762 | 3400 | 0.3000 |
122
+ | 0.6406 | 41.0714 | 3450 | 0.3001 |
123
+ | 0.657 | 41.6667 | 3500 | 0.2996 |
124
+ | 0.6353 | 42.2619 | 3550 | 0.2998 |
125
+ | 0.6369 | 42.8571 | 3600 | 0.2999 |
126
+ | 0.6314 | 43.4524 | 3650 | 0.2997 |
127
+ | 0.634 | 44.0476 | 3700 | 0.2992 |
128
+ | 0.6506 | 44.6429 | 3750 | 0.3010 |
129
+ | 0.63 | 45.2381 | 3800 | 0.2993 |
130
+ | 0.6395 | 45.8333 | 3850 | 0.2997 |
131
+ | 0.6393 | 46.4286 | 3900 | 0.2983 |
132
+ | 0.6344 | 47.0238 | 3950 | 0.2998 |
133
+ | 0.6432 | 47.6190 | 4000 | 0.2993 |
134
 
135
 
136
  ### Framework versions
137
 
138
+ - Transformers 4.47.0.dev0
139
  - Pytorch 2.4.0
140
  - Datasets 3.0.1
141
  - Tokenizers 0.20.0
config.json CHANGED
@@ -85,7 +85,7 @@
85
  "speech_decoder_prenet_layers": 2,
86
  "speech_decoder_prenet_units": 256,
87
  "torch_dtype": "float32",
88
- "transformers_version": "4.46.0.dev0",
89
  "use_cache": false,
90
  "use_guided_attention_loss": true,
91
  "vocab_size": 81
 
85
  "speech_decoder_prenet_layers": 2,
86
  "speech_decoder_prenet_units": 256,
87
  "torch_dtype": "float32",
88
+ "transformers_version": "4.47.0.dev0",
89
  "use_cache": false,
90
  "use_guided_attention_loss": true,
91
  "vocab_size": 81
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
- "transformers_version": "4.46.0.dev0"
9
  }
 
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
+ "transformers_version": "4.47.0.dev0"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b91ef8f9031d4dd9eaa399011ca7c2731f72fcb5c2fee189c83febbaccdb919a
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab12d28f1bf0a8310298b67604a638b4ca422315284e42a9019ece275e12e30
3
  size 577789320
runs/Oct25_11-39-41_715a232379e0/events.out.tfevents.1729856395.715a232379e0.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20156458eca5190234c480e0cdbffa92fd61ee8740aed1d3f0a74c341aa396dd
3
+ size 62415
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4260b6cedfe0b082fce2bf0abf6e442288b523662fabd6509f51106a36618b9
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac6e4b1088d7c2285789c1414175ef7687b4e17cc077befaaf7f2aa24f8ac8d
3
  size 5432