shahdelrefai commited on
Commit
faa2410
·
verified ·
1 Parent(s): 1ebc41c

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/speecht5_tts
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - voxpopuli
9
+ model-index:
10
+ - name: speecht5_finetuned_voxpopuli_en
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # speecht5_finetuned_voxpopuli_en
18
+
19
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - eval_loss: 0.4671
22
+ - eval_runtime: 123.5272
23
+ - eval_samples_per_second: 9.512
24
+ - eval_steps_per_second: 4.76
25
+ - epoch: 6.044
26
+ - step: 2000
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 4
47
+ - eval_batch_size: 2
48
+ - seed: 42
49
+ - gradient_accumulation_steps: 8
50
+ - total_train_batch_size: 32
51
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
+ - training_steps: 4000
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.47.1
60
+ - Pytorch 2.5.1+cu121
61
+ - Datasets 3.2.0
62
+ - Tokenizers 0.21.0
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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": "4.47.1"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b186fca16b92b8717738aa28585f27d16484a839ccf732224d222de01d21ade
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf9bfe704b32edc608054588f0de1770fe8c40f009eca57ae0eba5b3b3e7776
3
  size 577789320
runs/Dec21_15-13-26_8c5a3800ab44/events.out.tfevents.1734794007.8c5a3800ab44.180.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7378ff5d80b3c57b5ea6d11cc05465b5527f701a160421191cd55908d35493ab
3
- size 24123
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069ba6c454fd32740acef43162353a4865876b44b7fb749920f85b6bf6d70cf8
3
+ size 26233