End of training
Browse files- README.md +101 -0
- generation_config.json +9 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- voxpopuli
|
| 8 |
+
model-index:
|
| 9 |
+
- name: speecht5_finetuned_voxpopuli_hu
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# speecht5_finetuned_voxpopuli_hu
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4309
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- training_steps: 4000
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.6932 | 0.54 | 100 | 0.6017 |
|
| 55 |
+
| 0.6325 | 1.07 | 200 | 0.5632 |
|
| 56 |
+
| 0.5817 | 1.61 | 300 | 0.5078 |
|
| 57 |
+
| 0.5326 | 2.15 | 400 | 0.4830 |
|
| 58 |
+
| 0.5247 | 2.69 | 500 | 0.4703 |
|
| 59 |
+
| 0.5094 | 3.22 | 600 | 0.4630 |
|
| 60 |
+
| 0.5023 | 3.76 | 700 | 0.4568 |
|
| 61 |
+
| 0.4997 | 4.3 | 800 | 0.4541 |
|
| 62 |
+
| 0.4974 | 4.84 | 900 | 0.4504 |
|
| 63 |
+
| 0.4915 | 5.37 | 1000 | 0.4495 |
|
| 64 |
+
| 0.4885 | 5.91 | 1100 | 0.4475 |
|
| 65 |
+
| 0.4779 | 6.45 | 1200 | 0.4437 |
|
| 66 |
+
| 0.484 | 6.98 | 1300 | 0.4439 |
|
| 67 |
+
| 0.4799 | 7.52 | 1400 | 0.4419 |
|
| 68 |
+
| 0.4783 | 8.06 | 1500 | 0.4410 |
|
| 69 |
+
| 0.4764 | 8.6 | 1600 | 0.4401 |
|
| 70 |
+
| 0.4757 | 9.13 | 1700 | 0.4396 |
|
| 71 |
+
| 0.4742 | 9.67 | 1800 | 0.4378 |
|
| 72 |
+
| 0.4713 | 10.21 | 1900 | 0.4363 |
|
| 73 |
+
| 0.4747 | 10.75 | 2000 | 0.4370 |
|
| 74 |
+
| 0.4719 | 11.28 | 2100 | 0.4356 |
|
| 75 |
+
| 0.4694 | 11.82 | 2200 | 0.4349 |
|
| 76 |
+
| 0.4706 | 12.36 | 2300 | 0.4345 |
|
| 77 |
+
| 0.4757 | 12.89 | 2400 | 0.4341 |
|
| 78 |
+
| 0.466 | 13.43 | 2500 | 0.4334 |
|
| 79 |
+
| 0.4648 | 13.97 | 2600 | 0.4332 |
|
| 80 |
+
| 0.4663 | 14.51 | 2700 | 0.4329 |
|
| 81 |
+
| 0.4644 | 15.04 | 2800 | 0.4323 |
|
| 82 |
+
| 0.4646 | 15.58 | 2900 | 0.4324 |
|
| 83 |
+
| 0.4641 | 16.12 | 3000 | 0.4319 |
|
| 84 |
+
| 0.4644 | 16.66 | 3100 | 0.4316 |
|
| 85 |
+
| 0.463 | 17.19 | 3200 | 0.4312 |
|
| 86 |
+
| 0.4651 | 17.73 | 3300 | 0.4317 |
|
| 87 |
+
| 0.4637 | 18.27 | 3400 | 0.4315 |
|
| 88 |
+
| 0.4585 | 18.8 | 3500 | 0.4308 |
|
| 89 |
+
| 0.4605 | 19.34 | 3600 | 0.4310 |
|
| 90 |
+
| 0.4586 | 19.88 | 3700 | 0.4301 |
|
| 91 |
+
| 0.4636 | 20.42 | 3800 | 0.4308 |
|
| 92 |
+
| 0.4616 | 20.95 | 3900 | 0.4308 |
|
| 93 |
+
| 0.4593 | 21.49 | 4000 | 0.4309 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.34.1
|
| 99 |
+
- Pytorch 2.1.0+cu121
|
| 100 |
+
- Datasets 2.14.6
|
| 101 |
+
- Tokenizers 0.14.1
|
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": "4.34.1"
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 577878778
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:447f9980da20f3ba2af8c4e21d57efada6265ea3bfabe6556c7352ce1cc6003a
|
| 3 |
size 577878778
|