End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/speecht5_tts
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: CollectedDataModel
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# CollectedDataModel
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4390
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- training_steps: 4000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 54 |
+
| 0.5567 | 0.9913 | 100 | 0.4913 |
|
| 55 |
+
| 0.5127 | 1.9827 | 200 | 0.4692 |
|
| 56 |
+
| 0.4915 | 2.9740 | 300 | 0.4562 |
|
| 57 |
+
| 0.4862 | 3.9653 | 400 | 0.4524 |
|
| 58 |
+
| 0.4745 | 4.9566 | 500 | 0.4483 |
|
| 59 |
+
| 0.4735 | 5.9480 | 600 | 0.4458 |
|
| 60 |
+
| 0.4681 | 6.9393 | 700 | 0.4397 |
|
| 61 |
+
| 0.4656 | 7.9306 | 800 | 0.4408 |
|
| 62 |
+
| 0.4576 | 8.9219 | 900 | 0.4336 |
|
| 63 |
+
| 0.4571 | 9.9133 | 1000 | 0.4343 |
|
| 64 |
+
| 0.451 | 10.9046 | 1100 | 0.4339 |
|
| 65 |
+
| 0.4517 | 11.8959 | 1200 | 0.4316 |
|
| 66 |
+
| 0.4432 | 12.8872 | 1300 | 0.4315 |
|
| 67 |
+
| 0.4448 | 13.8786 | 1400 | 0.4357 |
|
| 68 |
+
| 0.4455 | 14.8699 | 1500 | 0.4296 |
|
| 69 |
+
| 0.4387 | 15.8612 | 1600 | 0.4331 |
|
| 70 |
+
| 0.4334 | 16.8525 | 1700 | 0.4359 |
|
| 71 |
+
| 0.4373 | 17.8439 | 1800 | 0.4290 |
|
| 72 |
+
| 0.4304 | 18.8352 | 1900 | 0.4318 |
|
| 73 |
+
| 0.4279 | 19.8265 | 2000 | 0.4305 |
|
| 74 |
+
| 0.4294 | 20.8178 | 2100 | 0.4327 |
|
| 75 |
+
| 0.4269 | 21.8092 | 2200 | 0.4327 |
|
| 76 |
+
| 0.4248 | 22.8005 | 2300 | 0.4309 |
|
| 77 |
+
| 0.4255 | 23.7918 | 2400 | 0.4275 |
|
| 78 |
+
| 0.43 | 24.7831 | 2500 | 0.4315 |
|
| 79 |
+
| 0.4214 | 25.7745 | 2600 | 0.4345 |
|
| 80 |
+
| 0.4166 | 26.7658 | 2700 | 0.4362 |
|
| 81 |
+
| 0.4173 | 27.7571 | 2800 | 0.4343 |
|
| 82 |
+
| 0.4172 | 28.7485 | 2900 | 0.4325 |
|
| 83 |
+
| 0.4142 | 29.7398 | 3000 | 0.4329 |
|
| 84 |
+
| 0.4134 | 30.7311 | 3100 | 0.4327 |
|
| 85 |
+
| 0.4121 | 31.7224 | 3200 | 0.4388 |
|
| 86 |
+
| 0.4085 | 32.7138 | 3300 | 0.4352 |
|
| 87 |
+
| 0.4095 | 33.7051 | 3400 | 0.4388 |
|
| 88 |
+
| 0.4112 | 34.6964 | 3500 | 0.4372 |
|
| 89 |
+
| 0.4106 | 35.6877 | 3600 | 0.4388 |
|
| 90 |
+
| 0.4054 | 36.6791 | 3700 | 0.4392 |
|
| 91 |
+
| 0.4075 | 37.6704 | 3800 | 0.4395 |
|
| 92 |
+
| 0.4086 | 38.6617 | 3900 | 0.4393 |
|
| 93 |
+
| 0.4125 | 39.6530 | 4000 | 0.4390 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.44.2
|
| 99 |
+
- Pytorch 2.4.1+cu121
|
| 100 |
+
- Datasets 3.0.1
|
| 101 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_length": 1876,
|
| 3 |
+
"transformers_version": "4.44.2"
|
| 4 |
+
}
|
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 sha256:3f905793c296be2c21d5cac1c3e9d8059e03d91a04254c9a140c768c04dc1421
|
| 3 |
size 577789320
|
runs/Oct07_17-14-25_7864c2fedeb2/events.out.tfevents.1728321286.7864c2fedeb2.248.0
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:e55112a6354601623c87022fca1148a8f711e1a069f65cd1b0f58c5c4a119f71
|
| 3 |
+
size 51498
|