Hugging Face's logo

fahadqazi
/
Sindhi-TTS

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
fahadqazi commited on
Commit
27d4a8f
•
1 Parent(s): 1a39ffb

Training in progress, step 500

Browse files
Files changed (3) hide show
  1. README.md +11 -22
  2. model.safetensors +1 -1
  3. runs/Nov14_22-31-18_6523109403c3/events.out.tfevents.1731623486.6523109403c3.199.4 +2 -2
README.md CHANGED
@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [MBZUAI/speecht5_tts_clartts_ar](https://huggingface.co/MBZUAI/speecht5_tts_clartts_ar) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5882
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -35,34 +40,18 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 5e-05
39
- - train_batch_size: 16
40
- - eval_batch_size: 2
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 32
44
  - optimizer: Use 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: 100
47
- - training_steps: 1000
48
  - mixed_precision_training: Native AMP
49
 
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 0.6706 | 0.1996 | 100 | 0.6716 |
55
- | 0.6365 | 0.3992 | 200 | 0.6357 |
56
- | 0.6266 | 0.5988 | 300 | 0.6185 |
57
- | 0.6172 | 0.7984 | 400 | 0.6162 |
58
- | 0.6011 | 0.9980 | 500 | 0.6083 |
59
- | 0.6047 | 1.1976 | 600 | 0.6041 |
60
- | 0.5943 | 1.3972 | 700 | 0.6023 |
61
- | 0.597 | 1.5968 | 800 | 0.5936 |
62
- | 0.5927 | 1.7964 | 900 | 0.5884 |
63
- | 0.5932 | 1.9960 | 1000 | 0.5882 |
64
-
65
-
66
  ### Framework versions
67
 
68
  - Transformers 4.46.2
 
16
 
17
  This model is a fine-tuned version of [MBZUAI/speecht5_tts_clartts_ar](https://huggingface.co/MBZUAI/speecht5_tts_clartts_ar) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 0.5724
20
+ - eval_runtime: 28.952
21
+ - eval_samples_per_second: 61.55
22
+ - eval_steps_per_second: 1.313
23
+ - epoch: 2.9940
24
+ - step: 500
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 0.0001
44
+ - train_batch_size: 48
45
+ - eval_batch_size: 48
46
  - seed: 42
47
  - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 96
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: 10000
53
  - mixed_precision_training: Native AMP
54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ### Framework versions
56
 
57
  - Transformers 4.46.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d06150be6d73b59cc9f165adbaaacb7d158a385905a42786703f06eb688196a
3
  size 617574792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4e0f160c2debc4d00573c204ca0485b8a1666ff8a8e30ef6bc12be47d8fc89
3
  size 617574792
runs/Nov14_22-31-18_6523109403c3/events.out.tfevents.1731623486.6523109403c3.199.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b97bca41c046581127298de35b2ec47283164950bf382005d5c77f11f18eecd
3
- size 11065
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019d8673d92cb3ed54a9dacf35ea245173e59d716eff9c51e753b24845221cbe
3
+ size 12180