TheMabrouk commited on
Commit
97a4cf9
1 Parent(s): 65c6d96

End of training

Browse files
Files changed (2) hide show
  1. README.md +64 -0
  2. generation_config.json +5 -1
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: MBZUAI/speecht5_tts_clartts_ar
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: speecht5_clartts_ar_finetuned_TTS-DATASET-V2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # speecht5_clartts_ar_finetuned_TTS-DATASET-V2
15
+
16
+ This model is a fine-tuned version of [MBZUAI/speecht5_tts_clartts_ar](https://huggingface.co/MBZUAI/speecht5_tts_clartts_ar) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.5535
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 2
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 32
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 500
46
+ - training_steps: 4000
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-------:|:----:|:---------------:|
53
+ | 0.5919 | 3.6832 | 1000 | 0.5715 |
54
+ | 0.5765 | 7.3665 | 2000 | 0.5579 |
55
+ | 0.5677 | 11.0497 | 3000 | 0.5536 |
56
+ | 0.5681 | 14.7330 | 4000 | 0.5535 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.42.0.dev0
62
+ - Pytorch 2.3.0+cu121
63
+ - Datasets 2.19.2
64
+ - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -1,5 +1,9 @@
1
  {
2
- "code_revision": "main",
 
 
3
  "eos_token_id": 2,
 
 
4
  "transformers_version": "4.42.0.dev0"
5
  }
 
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": "4.42.0.dev0"
9
  }