Hugging Face's logo

Solo448
/
SpeechT5-tuned-bn

Text-to-Audio
Transformers
TensorBoard
Safetensors
Bengali
speecht5
Bengali
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Solo448 commited on
Commit
fc3151d
·
verified ·
1 Parent(s): d644711

End of training

Browse files
Files changed (4) hide show
  1. README.md +22 -21
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Nov04_15-19-12_6c2120810ec4/events.out.tfevents.1730733555.6c2120810ec4.247.0 +2 -2
README.md CHANGED
@@ -21,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the train-bn dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.5622
25
 
26
  ## Model description
27
 
@@ -49,34 +49,35 @@ The following hyperparameters were used during training:
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 100
52
- - num_epochs: 3.0
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss |
58
  |:-------------:|:------:|:----:|:---------------:|
59
- | 6.2372 | 0.1803 | 100 | 0.7144 |
60
- | 5.5988 | 0.3607 | 200 | 0.6772 |
61
- | 5.4093 | 0.5410 | 300 | 0.6321 |
62
- | 5.3172 | 0.7214 | 400 | 0.6306 |
63
- | 5.1628 | 0.9017 | 500 | 0.6069 |
64
- | 5.1058 | 1.0821 | 600 | 0.6035 |
65
- | 5.0202 | 1.2624 | 700 | 0.5955 |
66
- | 5.0445 | 1.4427 | 800 | 0.5878 |
67
- | 4.9277 | 1.6231 | 900 | 0.5814 |
68
- | 4.9124 | 1.8034 | 1000 | 0.5767 |
69
- | 4.877 | 1.9838 | 1100 | 0.5764 |
70
- | 4.8186 | 2.1641 | 1200 | 0.5672 |
71
- | 4.7883 | 2.3445 | 1300 | 0.5692 |
72
- | 4.7329 | 2.5248 | 1400 | 0.5635 |
73
- | 4.8234 | 2.7051 | 1500 | 0.5598 |
74
- | 4.7006 | 2.8855 | 1600 | 0.5622 |
 
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.46.0.dev0
80
- - Pytorch 2.4.1+cu121
81
- - Datasets 3.0.1
82
  - Tokenizers 0.20.1
 
21
 
22
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the train-bn dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.5572
25
 
26
  ## Model description
27
 
 
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 100
52
+ - training_steps: 1700
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss |
58
  |:-------------:|:------:|:----:|:---------------:|
59
+ | 0.7601 | 0.1779 | 100 | 0.6865 |
60
+ | 0.7091 | 0.3559 | 200 | 0.6498 |
61
+ | 0.6819 | 0.5338 | 300 | 0.6345 |
62
+ | 0.6561 | 0.7117 | 400 | 0.6350 |
63
+ | 0.6353 | 0.8897 | 500 | 0.6044 |
64
+ | 0.6393 | 1.0676 | 600 | 0.5887 |
65
+ | 0.6402 | 1.2456 | 700 | 0.5906 |
66
+ | 0.6194 | 1.4235 | 800 | 0.5867 |
67
+ | 0.6127 | 1.6014 | 900 | 0.5788 |
68
+ | 0.608 | 1.7794 | 1000 | 0.5765 |
69
+ | 0.6129 | 1.9573 | 1100 | 0.5738 |
70
+ | 0.6044 | 2.1352 | 1200 | 0.5680 |
71
+ | 0.5894 | 2.3132 | 1300 | 0.5655 |
72
+ | 0.5952 | 2.4911 | 1400 | 0.5648 |
73
+ | 0.5963 | 2.6690 | 1500 | 0.5572 |
74
+ | 0.5889 | 2.8470 | 1600 | 0.5614 |
75
+ | 0.5897 | 3.0249 | 1700 | 0.5572 |
76
 
77
 
78
  ### Framework versions
79
 
80
+ - Transformers 4.47.0.dev0
81
+ - Pytorch 2.5.0+cu121
82
+ - Datasets 3.1.0
83
  - Tokenizers 0.20.1
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 sha256:8a967a64ea2394aa5688fb09c294ed1ce8f69f1b6506b86c963c14a9b36ab977
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6429926f0b5372ade63af2e544774a6a435d8d99deae0133baa29d086937d03e
3
  size 577789320
runs/Nov04_15-19-12_6c2120810ec4/events.out.tfevents.1730733555.6c2120810ec4.247.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b85b90e06cc3194aa276eefb6d3ca91591ee1ac42f3c66b94b0b39ebf36ac4c
3
- size 25635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe1a55c2230ff2d4a9f3da566b4d7c6fd650224806c217e3492825307178687
3
+ size 25989