Hugging Face's logo

Pooya-Fallah
/
speecht5_finetuned_PersianTTS

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Pooya-Fallah commited on
Commit
f1e7f0d
•
1 Parent(s): 3bb0faa

End of training

Browse files
Files changed (6) hide show
  1. README.md +16 -7
  2. model.safetensors +1 -1
  3. runs/Jun06_10-51-08_85e77a83553b/events.out.tfevents.1717671069.85e77a83553b.271.0 +3 -0
  4. runs/Jun06_10-56-05_85e77a83553b/events.out.tfevents.1717671367.85e77a83553b.271.1 +3 -0
  5. runs/Jun06_10-56-14_85e77a83553b/events.out.tfevents.1717671374.85e77a83553b.271.2 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.5398
19
- - eval_runtime: 310.9705
20
- - eval_samples_per_second: 33.952
21
- - eval_steps_per_second: 16.976
22
- - epoch: 1.2322
23
- - step: 1600
24
 
25
  ## Model description
26
 
@@ -50,9 +45,23 @@ The following hyperparameters were used during training:
50
  - lr_scheduler_warmup_steps: 500
51
  - training_steps: 2000
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  ### Framework versions
54
 
55
  - Transformers 4.42.0.dev0
56
  - Pytorch 2.3.0+cu121
57
- - Datasets 2.19.1
58
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5380
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
45
  - lr_scheduler_warmup_steps: 500
46
  - training_steps: 2000
47
 
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:----:|:---------------:|
52
+ | 0.9582 | 0.1925 | 250 | 0.6677 |
53
+ | 0.6618 | 0.3851 | 500 | 0.5812 |
54
+ | 0.586 | 0.5776 | 750 | 0.5595 |
55
+ | 0.5617 | 0.7701 | 1000 | 0.5486 |
56
+ | 0.5547 | 0.9626 | 1250 | 0.5420 |
57
+ | 0.5429 | 1.1552 | 1500 | 0.5411 |
58
+ | 0.5372 | 1.3477 | 1750 | 0.5377 |
59
+ | 0.5365 | 1.5402 | 2000 | 0.5380 |
60
+
61
+
62
  ### Framework versions
63
 
64
  - Transformers 4.42.0.dev0
65
  - Pytorch 2.3.0+cu121
66
+ - Datasets 2.19.2
67
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2494e380251defb1bdebd806cc3dea8d27ccf86eda9e070281ef17dd8df0f792
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da77118c75ba1f2a2d5ff1e7123679a235eb0dc2953e080296814b67890c3af5
3
  size 577789320
runs/Jun06_10-51-08_85e77a83553b/events.out.tfevents.1717671069.85e77a83553b.271.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630fdadc7cc17524b47f97c46c6b73f6d1eda7bce940c10a0170f9ab60be8052
3
+ size 6512
runs/Jun06_10-56-05_85e77a83553b/events.out.tfevents.1717671367.85e77a83553b.271.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51a9afe9e69c5888561fab78e1a05f077e60d3ee4850a749e882541e8dd2289
3
+ size 6511
runs/Jun06_10-56-14_85e77a83553b/events.out.tfevents.1717671374.85e77a83553b.271.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc75e36589b93b5bf8488023e4882efc9424d98e236730b99d7ae98bfc3a811
3
+ size 10722
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:632807dc6615dba0d2774c23f3c86141b79186dde799623bfaa0fc68d5848e07
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71117d59a23d1eaaf6b03c8894693f7bd5c8972375398c7973213d6c1f7c260c
3
  size 5304