End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: EGY1.5K
|
| 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 |
+
# EGY1.5K
|
| 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: 0.4590
|
| 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: 0.0001
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 16
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 100
|
| 46 |
+
- training_steps: 3000
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.5688 | 1.48 | 100 | 0.5112 |
|
| 54 |
+
| 0.5301 | 2.96 | 200 | 0.4908 |
|
| 55 |
+
| 0.5023 | 4.44 | 300 | 0.4707 |
|
| 56 |
+
| 0.524 | 5.93 | 400 | 0.4797 |
|
| 57 |
+
| 0.5001 | 7.41 | 500 | 0.4712 |
|
| 58 |
+
| 0.4774 | 8.89 | 600 | 0.4690 |
|
| 59 |
+
| 0.4793 | 10.37 | 700 | 0.4627 |
|
| 60 |
+
| 0.4666 | 11.85 | 800 | 0.4657 |
|
| 61 |
+
| 0.4649 | 13.33 | 900 | 0.4599 |
|
| 62 |
+
| 0.4659 | 14.81 | 1000 | 0.4616 |
|
| 63 |
+
| 0.4557 | 16.3 | 1100 | 0.4532 |
|
| 64 |
+
| 0.4516 | 17.78 | 1200 | 0.4535 |
|
| 65 |
+
| 0.4489 | 19.26 | 1300 | 0.4572 |
|
| 66 |
+
| 0.4431 | 20.74 | 1400 | 0.4504 |
|
| 67 |
+
| 0.4488 | 22.22 | 1500 | 0.4543 |
|
| 68 |
+
| 0.4452 | 23.7 | 1600 | 0.4557 |
|
| 69 |
+
| 0.4386 | 25.19 | 1700 | 0.4549 |
|
| 70 |
+
| 0.4297 | 26.67 | 1800 | 0.4487 |
|
| 71 |
+
| 0.4327 | 28.15 | 1900 | 0.4559 |
|
| 72 |
+
| 0.425 | 29.63 | 2000 | 0.4572 |
|
| 73 |
+
| 0.4251 | 31.11 | 2100 | 0.4531 |
|
| 74 |
+
| 0.4295 | 32.59 | 2200 | 0.4500 |
|
| 75 |
+
| 0.4258 | 34.07 | 2300 | 0.4561 |
|
| 76 |
+
| 0.4222 | 35.56 | 2400 | 0.4550 |
|
| 77 |
+
| 0.4119 | 37.04 | 2500 | 0.4569 |
|
| 78 |
+
| 0.4208 | 38.52 | 2600 | 0.4573 |
|
| 79 |
+
| 0.4145 | 40.0 | 2700 | 0.4568 |
|
| 80 |
+
| 0.4215 | 41.48 | 2800 | 0.4585 |
|
| 81 |
+
| 0.4141 | 42.96 | 2900 | 0.4594 |
|
| 82 |
+
| 0.4136 | 44.44 | 3000 | 0.4590 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.39.3
|
| 88 |
+
- Pytorch 2.3.0+cu118
|
| 89 |
+
- Datasets 3.0.0
|
| 90 |
+
- Tokenizers 0.15.2
|
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": "4.39.3"
|
| 9 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 577789320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8ac6485f513b18acc9752d63310572cd48d7b0adf3eb05f5a487014e1c3dd7b
|
| 3 |
size 577789320
|
runs/Oct23_11-28-44_DESKTOP-2JMMFKH/events.out.tfevents.1729672128.DESKTOP-2JMMFKH
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4762cf14b6f89cb7d357e2b691454f8dd279931dec8390f87b512eaf2178951
|
| 3 |
+
size 77914
|