Model save
Browse files- README.md +91 -0
- generation_config.json +9 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: speecht5_dhivehi_tts_v8_from_scratch
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# speecht5_dhivehi_tts_v8_from_scratch
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.7747
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 128
|
| 38 |
+
- eval_batch_size: 32
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 256
|
| 42 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: cosine_with_restarts
|
| 44 |
+
- lr_scheduler_warmup_steps: 2000
|
| 45 |
+
- training_steps: 100000
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:--------:|:-----:|:---------------:|
|
| 52 |
+
| 1.3751 | 22.9942 | 2000 | 1.3367 |
|
| 53 |
+
| 1.3348 | 45.9827 | 4000 | 1.3422 |
|
| 54 |
+
| 1.2871 | 68.9711 | 6000 | 1.3045 |
|
| 55 |
+
| 1.2354 | 91.9595 | 8000 | 1.2275 |
|
| 56 |
+
| 1.1849 | 114.9480 | 10000 | 1.1799 |
|
| 57 |
+
| 1.1335 | 137.9364 | 12000 | 1.1210 |
|
| 58 |
+
| 1.0861 | 160.9249 | 14000 | 1.0787 |
|
| 59 |
+
| 0.9836 | 183.9133 | 16000 | 1.0411 |
|
| 60 |
+
| 0.8547 | 206.9017 | 18000 | 1.0122 |
|
| 61 |
+
| 0.799 | 229.8902 | 20000 | 1.0109 |
|
| 62 |
+
| 0.7594 | 252.8786 | 22000 | 0.9857 |
|
| 63 |
+
| 0.7332 | 275.8671 | 24000 | 0.9696 |
|
| 64 |
+
| 0.7104 | 298.8555 | 26000 | 0.9611 |
|
| 65 |
+
| 0.6849 | 321.8439 | 28000 | 0.9329 |
|
| 66 |
+
| 0.6566 | 344.8324 | 30000 | 0.9309 |
|
| 67 |
+
| 0.634 | 367.8208 | 32000 | 0.8978 |
|
| 68 |
+
| 0.6138 | 390.8092 | 34000 | 0.8874 |
|
| 69 |
+
| 0.5951 | 413.7977 | 36000 | 0.8814 |
|
| 70 |
+
| 0.5785 | 436.7861 | 38000 | 0.8510 |
|
| 71 |
+
| 0.5617 | 459.7746 | 40000 | 0.8569 |
|
| 72 |
+
| 0.5484 | 482.7630 | 42000 | 0.8135 |
|
| 73 |
+
| 0.5349 | 505.7514 | 44000 | 0.8215 |
|
| 74 |
+
| 0.5247 | 528.7399 | 46000 | 0.8190 |
|
| 75 |
+
| 0.5134 | 551.7283 | 48000 | 0.8198 |
|
| 76 |
+
| 0.505 | 574.7168 | 50000 | 0.7792 |
|
| 77 |
+
| 0.494 | 597.7052 | 52000 | 0.8174 |
|
| 78 |
+
| 0.4862 | 620.6936 | 54000 | 0.7625 |
|
| 79 |
+
| 0.4783 | 643.6821 | 56000 | 0.7940 |
|
| 80 |
+
| 0.4731 | 666.6705 | 58000 | 0.7974 |
|
| 81 |
+
| 0.4667 | 689.6590 | 60000 | 0.7664 |
|
| 82 |
+
| 0.4621 | 712.6474 | 62000 | 0.7744 |
|
| 83 |
+
| 0.4554 | 735.6358 | 64000 | 0.7747 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.48.0.dev0
|
| 89 |
+
- Pytorch 2.5.1+cu121
|
| 90 |
+
- Datasets 3.2.0
|
| 91 |
+
- 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": "4.48.0.dev0"
|
| 9 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 608260488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37c1bd67772b5c17b7775baaa12b0ca3cb77c48a6afb4735463f5633bccba06c
|
| 3 |
size 608260488
|